[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-12d4645cb79c340d-optimizing-cnn-pruning-with-multi-armed-bandits-summary":3,"summaries-facets-categories":100,"summary-related-12d4645cb79c340d-optimizing-cnn-pruning-with-multi-armed-bandits-summary":5986},{"id":4,"title":5,"ai":6,"body":13,"categories":67,"created_at":69,"date_modified":69,"description":62,"extension":70,"faq":69,"featured":71,"kicker_label":69,"meta":72,"navigation":84,"path":85,"published_at":86,"question":69,"scraped_at":86,"seo":87,"sitemap":88,"source_id":89,"source_name":90,"source_type":91,"source_url":77,"stem":92,"tags":93,"thumbnail_url":69,"tldr":97,"tweet":69,"unknown_tags":98,"__hash__":99},"summaries\u002Fsummaries\u002F12d4645cb79c340d-optimizing-cnn-pruning-with-multi-armed-bandits-summary.md","Optimizing CNN Pruning with Multi-Armed Bandits",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","google\u002Fgemini-3.1-flash-lite",4038,538,2810,0.0018165,{"type":14,"value":15,"toc":61},"minimark",[16,21,25,29,32,35,58],[17,18,20],"h2",{"id":19},"balancing-model-compression-and-accuracy","Balancing Model Compression and Accuracy",[22,23,24],"p",{},"Pruning convolutional neural networks (CNNs) is a critical task for deploying models on resource-constrained hardware. Traditional pruning methods often rely on static heuristics—such as weight magnitude or activation variance—to determine which feature maps to remove. These methods frequently fail to account for the complex, non-linear relationship between specific feature maps and the final loss function. The authors propose a dynamic, loss-aware approach that treats the pruning process as a decision-making problem under uncertainty.",[17,26,28],{"id":27},"the-multi-armed-bandit-framework-for-pruning","The Multi-Armed Bandit Framework for Pruning",[22,30,31],{},"To solve the selection problem, the authors frame feature-map pruning as a Multi-Armed Bandit (MAB) challenge. In this setup, each potential pruning candidate (a feature map) is treated as an 'arm.' The goal is to maximize the compression ratio while minimizing the impact on the model's loss.",[22,33,34],{},"Key components of this approach include:",[36,37,38,46,52],"ul",{},[39,40,41,45],"li",{},[42,43,44],"strong",{},"Dynamic Selection",": Unlike static pruning, the MAB agent observes the impact of removing specific feature maps on the loss function in real-time, allowing it to learn which maps are truly redundant.",[39,47,48,51],{},[42,49,50],{},"Exploration vs. Exploitation",": The algorithm balances the need to test various pruning configurations (exploration) with the need to commit to the most efficient pruning strategy (exploitation). This prevents the model from getting stuck in suboptimal local minima during the compression phase.",[39,53,54,57],{},[42,55,56],{},"Loss-Aware Feedback",": By directly incorporating the loss function into the reward signal for the bandit, the method ensures that the pruning process is sensitive to the specific task performance, rather than just structural properties of the network.",[22,59,60],{},"This approach effectively mitigates the 'greedy' nature of traditional pruning, where removing one map might seem optimal in isolation but causes significant performance drops when combined with other removals. By using the MAB framework, the system learns the interdependencies between feature maps, leading to more robust and accurate compressed models.",{"title":62,"searchDepth":63,"depth":63,"links":64},"",2,[65,66],{"id":19,"depth":63,"text":20},{"id":27,"depth":63,"text":28},[68],"Data Science & Visualization",null,"md",false,{"content_references":73,"triage":79},[74],{"type":75,"title":76,"url":77,"context":78},"paper","Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.22564","reviewed",{"relevance":80,"novelty":81,"quality":81,"actionability":63,"composite":82,"reasoning":83},3,4,3.25,"Category: AI & LLMs. The article discusses a novel approach to CNN pruning using multi-armed bandits, which is relevant to AI engineering and addresses a specific technical challenge in model optimization. However, while it presents new insights, it lacks practical steps that the audience can directly implement.",true,"\u002Fsummaries\u002F12d4645cb79c340d-optimizing-cnn-pruning-with-multi-armed-bandits-summary","2026-07-29 03:12:17",{"title":5,"description":62},{"loc":85},"12d4645cb79c340d","arXiv cs.AI","article","summaries\u002F12d4645cb79c340d-optimizing-cnn-pruning-with-multi-armed-bandits-summary",[94,95,96],"machine-learning","deep-learning","research","This paper introduces a loss-aware pruning strategy for convolutional neural networks that uses multi-armed bandits to dynamically identify and remove redundant feature maps while minimizing accuracy degradation.",[],"DAZYQMCQbI1bidwiVIs78fX0MtXBSjsbVsreFQuxQ-4",[101,104,107,110,112,115,118,120,122,124,127,129,131,133,135,138,140,142,144,146,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,190,192,194,196,198,200,202,204,206,208,210,212,214,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,252,254,256,258,260,262,264,266,268,270,272,274,276,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,338,340,342,344,346,348,350,352,354,356,359,361,363,365,367,369,371,373,375,377,379,381,383,386,388,390,392,394,396,398,400,402,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,456,458,460,463,465,467,469,471,473,475,477,479,481,483,485,487,489,492,494,496,498,500,502,504,506,508,510,512,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,762,764,766,768,770,773,775,777,779,781,783,785,787,789,791,793,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701,3703,3705,3707,3709,3711,3713,3715,3717,3719,3721,3723,3725,3727,3729,3731,3733,3735,3737,3739,3741,3743,3745,3747,3749,3751,3753,3755,3757,3759,3761,3763,3765,3767,3769,3771,3773,3775,3777,3779,3781,3783,3785,3787,3789,3791,3793,3795,3797,3799,3801,3803,3805,3807,3809,3811,3813,3815,3817,3819,3821,3823,3825,3827,3829,3831,3833,3835,3837,3839,3841,3843,3845,3847,3849,3851,3853,3855,3857,3859,3861,3863,3866,3868,3870,3872,3874,3876,3878,3880,3882,3884,3886,3888,3890,3892,3894,3896,3898,3900,3902,3904,3906,3908,3910,3912,3914,3916,3918,3920,3922,3924,3926,3928,3930,3932,3934,3936,3938,3940,3942,3944,3946,3948,3950,3952,3954,3956,3958,3960,3962,3964,3966,3968,3970,3972,3974,3976,3978,3980,3982,3984,3986,3988,3990,3992,3994,3996,3998,4000,4002,4004,4006,4008,4010,4012,4014,4016,4018,4020,4022,4024,4026,4028,4030,4032,4034,4036,4038,4040,4042,4044,4046,4048,4050,4052,4054,4056,4058,4060,4062,4064,4066,4068,4070,4072,4074,4076,4078,4080,4082,4084,4086,4088,4090,4092,4094,4096,4098,4100,4102,4104,4106,4108,4110,4112,4114,4116,4118,4120,4122,4124,4126,4128,4130,4132,4134,4136,4138,4140,4142,4144,4146,4148,4150,4152,4154,4156,4158,4160,4162,4164,4166,4168,4170,4172,4174,4176,4178,4180,4182,4184,4186,4188,4190,4192,4194,4196,4198,4200,4202,4204,4206,4208,4210,4212,4214,4216,4218,4220,4222,4224,4226,4228,4230,4232,4234,4236,4238,4240,4242,4244,4246,4248,4250,4252,4254,4256,4258,4260,4262,4264,4266,4268,4270,4272,4274,4276,4278,4280,4282,4284,4286,4288,4290,4292,4294,4296,4298,4300,4302,4304,4306,4308,4310,4312,4314,4316,4318,4320,4322,4324,4326,4328,4330,4332,4334,4336,4338,4340,4342,4344,4346,4348,4350,4352,4354,4356,4358,4360,4362,4364,4366,4368,4370,4372,4374,4376,4378,4380,4382,4384,4386,4388,4390,4392,4394,4396,4398,4400,4402,4404,4406,4408,4410,4412,4414,4416,4418,4420,4422,4424,4426,4428,4430,4432,4434,4436,4438,4440,4442,4444,4446,4448,4450,4452,4454,4456,4458,4460,4462,4464,4466,4468,4470,4472,4474,4476,4478,4480,4482,4484,4486,4488,4490,4492,4494,4496,4498,4500,4502,4504,4506,4508,4510,4512,4514,4516,4518,4520,4522,4524,4526,4528,4530,4532,4534,4536,4538,4540,4542,4544,4546,4548,4550,4552,4554,4556,4558,4560,4562,4564,4566,4568,4570,4572,4574,4576,4578,4580,4582,4584,4586,4588,4590,4592,4594,4596,4598,4600,4602,4605,4607,4609,4611,4613,4615,4617,4619,4621,4623,4625,4627,4629,4631,4633,4635,4637,4639,4641,4643,4645,4647,4649,4651,4653,4655,4657,4659,4661,4663,4665,4667,4669,4671,4673,4675,4677,4679,4681,4683,4685,4687,4689,4691,4693,4695,4697,4699,4701,4703,4705,4707,4709,4711,4713,4715,4717,4719,4721,4723,4725,4727,4729,4731,4733,4735,4737,4739,4741,4743,4745,4747,4749,4751,4753,4755,4757,4759,4761,4763,4765,4767,4769,4772,4774,4776,4778,4780,4782,4784,4786,4788,4790,4792,4794,4796,4798,4800,4802,4804,4806,4808,4810,4812,4814,4816,4818,4820,4822,4824,4826,4828,4830,4832,4834,4836,4838,4840,4842,4844,4846,4848,4850,4852,4854,4856,4858,4860,4862,4864,4866,4868,4870,4872,4874,4876,4878,4880,4882,4884,4886,4888,4890,4892,4894,4896,4898,4900,4902,4904,4906,4908,4910,4912,4914,4916,4918,4920,4922,4924,4926,4928,4930,4932,4934,4936,4938,4940,4942,4944,4946,4948,4950,4952,4954,4956,4958,4960,4962,4964,4966,4968,4970,4972,4974,4976,4978,4980,4982,4984,4986,4988,4990,4992,4994,4996,4998,5000,5002,5004,5006,5008,5010,5012,5014,5016,5018,5020,5022,5024,5026,5028,5030,5032,5034,5036,5038,5040,5042,5044,5046,5048,5050,5052,5054,5056,5058,5060,5062,5064,5066,5068,5070,5072,5074,5076,5078,5080,5082,5084,5086,5088,5090,5092,5094,5096,5098,5100,5102,5104,5106,5108,5110,5112,5114,5116,5118,5120,5122,5124,5126,5128,5130,5132,5134,5136,5138,5140,5142,5144,5146,5148,5150,5152,5154,5156,5158,5160,5162,5164,5166,5168,5170,5172,5174,5176,5178,5180,5182,5184,5186,5188,5190,5192,5194,5196,5198,5200,5202,5204,5206,5208,5210,5212,5214,5216,5218,5220,5222,5224,5226,5228,5230,5232,5234,5236,5238,5240,5242,5244,5246,5248,5250,5252,5254,5256,5258,5260,5262,5264,5266,5268,5270,5272,5274,5276,5278,5280,5282,5284,5286,5288,5290,5292,5294,5296,5298,5300,5302,5304,5306,5308,5310,5312,5314,5316,5318,5320,5322,5324,5326,5328,5330,5332,5334,5336,5338,5340,5342,5344,5346,5348,5350,5352,5354,5356,5358,5360,5362,5364,5366,5368,5370,5372,5374,5376,5378,5380,5382,5384,5386,5388,5390,5392,5394,5396,5398,5400,5402,5404,5406,5408,5410,5412,5414,5416,5418,5420,5422,5424,5426,5428,5430,5432,5434,5436,5438,5440,5442,5444,5446,5448,5450,5452,5454,5456,5458,5460,5462,5464,5466,5468,5470,5472,5474,5476,5478,5480,5482,5484,5486,5488,5490,5492,5494,5496,5498,5500,5502,5504,5506,5508,5510,5512,5514,5516,5518,5520,5522,5524,5526,5528,5530,5532,5534,5536,5538,5540,5542,5544,5546,5548,5550,5552,5554,5556,5558,5560,5562,5564,5566,5568,5570,5572,5574,5576,5578,5580,5582,5584,5586,5588,5590,5592,5594,5596,5598,5600,5602,5604,5606,5608,5610,5612,5614,5616,5618,5620,5622,5624,5626,5628,5630,5632,5634,5636,5638,5640,5642,5644,5646,5648,5650,5652,5654,5656,5658,5660,5662,5664,5666,5668,5670,5672,5674,5676,5678,5680,5682,5684,5686,5688,5690,5692,5694,5696,5698,5700,5702,5704,5706,5708,5710,5712,5714,5716,5718,5720,5722,5724,5726,5728,5730,5732,5734,5736,5738,5740,5742,5744,5746,5748,5750,5752,5754,5756,5758,5760,5762,5764,5766,5768,5770,5772,5774,5776,5778,5780,5782,5784,5786,5788,5790,5792,5794,5796,5798,5800,5802,5804,5806,5808,5810,5812,5814,5816,5818,5820,5822,5824,5826,5828,5830,5832,5834,5836,5838,5840,5842,5844,5846,5848,5850,5852,5854,5856,5858,5860,5862,5864,5866,5868,5870,5872,5874,5876,5878,5880,5882,5884,5886,5888,5890,5892,5894,5896,5898,5900,5902,5904,5906,5908,5910,5912,5914,5916,5918,5920,5922,5924,5926,5928,5930,5932,5934,5936,5938,5940,5942,5944,5946,5948,5950,5952,5954,5956,5958,5960,5962,5964,5966,5968,5970,5972,5974,5976,5978,5980,5982,5984],{"categories":102},[103],"AI & LLMs",{"categories":105},[106],"Developer Productivity",{"categories":108},[109],"Business & SaaS",{"categories":111},[103],{"categories":113},[114],"AI Automation",{"categories":116},[117],"Product Strategy",{"categories":119},[103],{"categories":121},[106],{"categories":123},[114],{"categories":125},[126],"Software Engineering",{"categories":128},[103],{"categories":130},[109],{"categories":132},[],{"categories":134},[103],{"categories":136},[137],"Inference & Serving",{"categories":139},[103],{"categories":141},[103],{"categories":143},[114],{"categories":145},[],{"categories":147},[148],"AI News & Trends",{"categories":150},[114],{"categories":152},[103],{"categories":154},[109],{"categories":156},[106],{"categories":158},[103],{"categories":160},[114],{"categories":162},[148],{"categories":164},[114],{"categories":166},[114],{"categories":168},[103],{"categories":170},[114],{"categories":172},[103],{"categories":174},[103],{"categories":176},[103],{"categories":178},[148],{"categories":180},[103],{"categories":182},[103],{"categories":184},[103],{"categories":186},[],{"categories":188},[189],"Design & Frontend",{"categories":191},[68],{"categories":193},[148],{"categories":195},[103],{"categories":197},[103],{"categories":199},[103],{"categories":201},[],{"categories":203},[103],{"categories":205},[114],{"categories":207},[126],{"categories":209},[103],{"categories":211},[114],{"categories":213},[103],{"categories":215},[216],"Marketing & Growth",{"categories":218},[189],{"categories":220},[103],{"categories":222},[114],{"categories":224},[103],{"categories":226},[126],{"categories":228},[],{"categories":230},[],{"categories":232},[189],{"categories":234},[103],{"categories":236},[114],{"categories":238},[106],{"categories":240},[126],{"categories":242},[189],{"categories":244},[117],{"categories":246},[103],{"categories":248},[126],{"categories":250},[251],"DevOps & Cloud",{"categories":253},[114],{"categories":255},[117],{"categories":257},[148],{"categories":259},[103],{"categories":261},[],{"categories":263},[103],{"categories":265},[],{"categories":267},[114],{"categories":269},[126],{"categories":271},[],{"categories":273},[126],{"categories":275},[103],{"categories":277},[278],"Governance & Standards",{"categories":280},[109],{"categories":282},[],{"categories":284},[],{"categories":286},[103],{"categories":288},[103],{"categories":290},[114],{"categories":292},[103],{"categories":294},[103],{"categories":296},[114],{"categories":298},[103],{"categories":300},[103],{"categories":302},[103],{"categories":304},[],{"categories":306},[126],{"categories":308},[],{"categories":310},[],{"categories":312},[126],{"categories":314},[],{"categories":316},[126],{"categories":318},[103],{"categories":320},[103],{"categories":322},[216],{"categories":324},[103],{"categories":326},[189],{"categories":328},[189],{"categories":330},[103],{"categories":332},[126],{"categories":334},[114],{"categories":336},[337],"GovTech & Public-Sector Adoption",{"categories":339},[126],{"categories":341},[103],{"categories":343},[103],{"categories":345},[114],{"categories":347},[114],{"categories":349},[68],{"categories":351},[103],{"categories":353},[148],{"categories":355},[114],{"categories":357},[358],"Legal AI Tools",{"categories":360},[114],{"categories":362},[216],{"categories":364},[114],{"categories":366},[117],{"categories":368},[126],{"categories":370},[337],{"categories":372},[],{"categories":374},[114],{"categories":376},[],{"categories":378},[109],{"categories":380},[114],{"categories":382},[114],{"categories":384},[385],"RAG & Retrieval",{"categories":387},[109],{"categories":389},[103],{"categories":391},[126],{"categories":393},[126],{"categories":395},[251],{"categories":397},[189],{"categories":399},[103],{"categories":401},[],{"categories":403},[404],"Agents & Orchestration",{"categories":406},[126],{"categories":408},[103],{"categories":410},[],{"categories":412},[114],{"categories":414},[109],{"categories":416},[],{"categories":418},[103],{"categories":420},[],{"categories":422},[106],{"categories":424},[126],{"categories":426},[109],{"categories":428},[103],{"categories":430},[103],{"categories":432},[148],{"categories":434},[103],{"categories":436},[],{"categories":438},[103],{"categories":440},[],{"categories":442},[126],{"categories":444},[103],{"categories":446},[68],{"categories":448},[],{"categories":450},[103],{"categories":452},[189],{"categories":454},[455],"Models & Frontier Labs",{"categories":457},[],{"categories":459},[189],{"categories":461},[462],"Regulation & Governance of AI",{"categories":464},[114],{"categories":466},[],{"categories":468},[103],{"categories":470},[103],{"categories":472},[114],{"categories":474},[148],{"categories":476},[109],{"categories":478},[103],{"categories":480},[],{"categories":482},[126],{"categories":484},[114],{"categories":486},[103],{"categories":488},[117],{"categories":490},[491],"AI Policy & Regulation",{"categories":493},[],{"categories":495},[103],{"categories":497},[117],{"categories":499},[114],{"categories":501},[103],{"categories":503},[103],{"categories":505},[103],{"categories":507},[114],{"categories":509},[],{"categories":511},[68],{"categories":513},[514],"Evals & Reliability",{"categories":516},[103],{"categories":518},[],{"categories":520},[106],{"categories":522},[337],{"categories":524},[491],{"categories":526},[103],{"categories":528},[109],{"categories":530},[103],{"categories":532},[114],{"categories":534},[103],{"categories":536},[114],{"categories":538},[404],{"categories":540},[103],{"categories":542},[126],{"categories":544},[103],{"categories":546},[],{"categories":548},[],{"categories":550},[103],{"categories":552},[337],{"categories":554},[103],{"categories":556},[103],{"categories":558},[],{"categories":560},[189],{"categories":562},[],{"categories":564},[103],{"categories":566},[],{"categories":568},[114],{"categories":570},[103],{"categories":572},[189],{"categories":574},[],{"categories":576},[103],{"categories":578},[114],{"categories":580},[103],{"categories":582},[109],{"categories":584},[114],{"categories":586},[103],{"categories":588},[103],{"categories":590},[126],{"categories":592},[189],{"categories":594},[114],{"categories":596},[],{"categories":598},[126],{"categories":600},[114],{"categories":602},[68],{"categories":604},[],{"categories":606},[148],{"categories":608},[],{"categories":610},[103],{"categories":612},[103],{"categories":614},[103],{"categories":616},[109,216],{"categories":618},[],{"categories":620},[103],{"categories":622},[103],{"categories":624},[114],{"categories":626},[],{"categories":628},[],{"categories":630},[103],{"categories":632},[189],{"categories":634},[103],{"categories":636},[],{"categories":638},[103],{"categories":640},[251],{"categories":642},[],{"categories":644},[114],{"categories":646},[148],{"categories":648},[103],{"categories":650},[189],{"categories":652},[],{"categories":654},[148],{"categories":656},[103],{"categories":658},[137],{"categories":660},[103],{"categories":662},[114],{"categories":664},[148],{"categories":666},[455],{"categories":668},[103],{"categories":670},[216],{"categories":672},[],{"categories":674},[114],{"categories":676},[109],{"categories":678},[126],{"categories":680},[103],{"categories":682},[114],{"categories":684},[],{"categories":686},[103,251],{"categories":688},[103],{"categories":690},[103],{"categories":692},[103],{"categories":694},[114],{"categories":696},[103,126],{"categories":698},[68],{"categories":700},[103],{"categories":702},[103],{"categories":704},[126],{"categories":706},[114],{"categories":708},[491],{"categories":710},[216],{"categories":712},[103],{"categories":714},[114],{"categories":716},[103],{"categories":718},[103],{"categories":720},[114],{"categories":722},[],{"categories":724},[114],{"categories":726},[103],{"categories":728},[103],{"categories":730},[114],{"categories":732},[103],{"categories":734},[103,109],{"categories":736},[109],{"categories":738},[],{"categories":740},[189],{"categories":742},[189],{"categories":744},[103],{"categories":746},[],{"categories":748},[],{"categories":750},[148],{"categories":752},[],{"categories":754},[106],{"categories":756},[103],{"categories":758},[126],{"categories":760},[761],"Generative UI & Design-to-Code",{"categories":763},[103],{"categories":765},[103],{"categories":767},[189],{"categories":769},[103],{"categories":771},[772],"Algorithmic Accountability",{"categories":774},[114],{"categories":776},[126],{"categories":778},[148],{"categories":780},[189],{"categories":782},[],{"categories":784},[117],{"categories":786},[103],{"categories":788},[103],{"categories":790},[103],{"categories":792},[114],{"categories":794},[795],"MLOps & Infrastructure",{"categories":797},[103],{"categories":799},[103],{"categories":801},[103],{"categories":803},[103],{"categories":805},[103],{"categories":807},[148],{"categories":809},[106],{"categories":811},[103],{"categories":813},[114],{"categories":815},[251],{"categories":817},[109],{"categories":819},[103],{"categories":821},[189],{"categories":823},[103],{"categories":825},[114],{"categories":827},[],{"categories":829},[],{"categories":831},[137],{"categories":833},[189],{"categories":835},[148],{"categories":837},[68],{"categories":839},[],{"categories":841},[103],{"categories":843},[103],{"categories":845},[109],{"categories":847},[114],{"categories":849},[103],{"categories":851},[103],{"categories":853},[103],{"categories":855},[148],{"categories":857},[137],{"categories":859},[103],{"categories":861},[189],{"categories":863},[],{"categories":865},[114],{"categories":867},[126],{"categories":869},[],{"categories":871},[103],{"categories":873},[103],{"categories":875},[114],{"categories":877},[126],{"categories":879},[103],{"categories":881},[68],{"categories":883},[],{"categories":885},[103],{"categories":887},[],{"categories":889},[103],{"categories":891},[],{"categories":893},[117],{"categories":895},[109],{"categories":897},[114],{"categories":899},[114],{"categories":901},[],{"categories":903},[106],{"categories":905},[103],{"categories":907},[103],{"categories":909},[109],{"categories":911},[148],{"categories":913},[106],{"categories":915},[],{"categories":917},[103],{"categories":919},[],{"categories":921},[],{"categories":923},[148],{"categories":925},[148],{"categories":927},[],{"categories":929},[404],{"categories":931},[103],{"categories":933},[189],{"categories":935},[126],{"categories":937},[],{"categories":939},[358],{"categories":941},[109],{"categories":943},[],{"categories":945},[],{"categories":947},[106],{"categories":949},[68],{"categories":951},[],{"categories":953},[216],{"categories":955},[114],{"categories":957},[109],{"categories":959},[114],{"categories":961},[109],{"categories":963},[126],{"categories":965},[],{"categories":967},[137],{"categories":969},[117],{"categories":971},[103],{"categories":973},[189],{"categories":975},[126],{"categories":977},[109],{"categories":979},[103],{"categories":981},[114],{"categories":983},[109],{"categories":985},[103],{"categories":987},[103],{"categories":989},[103],{"categories":991},[103],{"categories":993},[],{"categories":995},[],{"categories":997},[126],{"categories":999},[68],{"categories":1001},[117],{"categories":1003},[103],{"categories":1005},[114],{"categories":1007},[103],{"categories":1009},[],{"categories":1011},[148],{"categories":1013},[117],{"categories":1015},[103],{"categories":1017},[514],{"categories":1019},[251],{"categories":1021},[],{"categories":1023},[114],{"categories":1025},[],{"categories":1027},[106],{"categories":1029},[],{"categories":1031},[103],{"categories":1033},[103],{"categories":1035},[189],{"categories":1037},[216],{"categories":1039},[126],{"categories":1041},[114],{"categories":1043},[],{"categories":1045},[126],{"categories":1047},[103],{"categories":1049},[106],{"categories":1051},[],{"categories":1053},[109],{"categories":1055},[148],{"categories":1057},[103,251],{"categories":1059},[1060],"Design Systems for AI",{"categories":1062},[103],{"categories":1064},[103],{"categories":1066},[148],{"categories":1068},[103],{"categories":1070},[103],{"categories":1072},[109],{"categories":1074},[103],{"categories":1076},[103],{"categories":1078},[],{"categories":1080},[103],{"categories":1082},[103],{"categories":1084},[109],{"categories":1086},[103],{"categories":1088},[],{"categories":1090},[114],{"categories":1092},[126],{"categories":1094},[148],{"categories":1096},[126],{"categories":1098},[189],{"categories":1100},[148],{"categories":1102},[68],{"categories":1104},[103],{"categories":1106},[106],{"categories":1108},[491],{"categories":1110},[103],{"categories":1112},[114],{"categories":1114},[103],{"categories":1116},[126],{"categories":1118},[126],{"categories":1120},[],{"categories":1122},[],{"categories":1124},[114],{"categories":1126},[117],{"categories":1128},[],{"categories":1130},[103],{"categories":1132},[],{"categories":1134},[189],{"categories":1136},[114],{"categories":1138},[126],{"categories":1140},[189],{"categories":1142},[103],{"categories":1144},[103],{"categories":1146},[189],{"categories":1148},[],{"categories":1150},[],{"categories":1152},[148],{"categories":1154},[114],{"categories":1156},[114],{"categories":1158},[103],{"categories":1160},[103],{"categories":1162},[103],{"categories":1164},[109],{"categories":1166},[103],{"categories":1168},[103],{"categories":1170},[],{"categories":1172},[126],{"categories":1174},[126],{"categories":1176},[103],{"categories":1178},[126],{"categories":1180},[109],{"categories":1182},[],{"categories":1184},[103],{"categories":1186},[103],{"categories":1188},[103],{"categories":1190},[103],{"categories":1192},[114],{"categories":1194},[106],{"categories":1196},[109],{"categories":1198},[148],{"categories":1200},[114],{"categories":1202},[137],{"categories":1204},[216],{"categories":1206},[103],{"categories":1208},[114],{"categories":1210},[],{"categories":1212},[189],{"categories":1214},[],{"categories":1216},[103],{"categories":1218},[103],{"categories":1220},[],{"categories":1222},[126],{"categories":1224},[109],{"categories":1226},[1227],"Visual & Generative Media",{"categories":1229},[114],{"categories":1231},[],{"categories":1233},[103],{"categories":1235},[103],{"categories":1237},[126],{"categories":1239},[251],{"categories":1241},[68],{"categories":1243},[491],{"categories":1245},[126],{"categories":1247},[216],{"categories":1249},[103],{"categories":1251},[189],{"categories":1253},[103],{"categories":1255},[103],{"categories":1257},[126],{"categories":1259},[114],{"categories":1261},[103],{"categories":1263},[],{"categories":1265},[],{"categories":1267},[114],{"categories":1269},[106],{"categories":1271},[114],{"categories":1273},[455],{"categories":1275},[103],{"categories":1277},[117],{"categories":1279},[103],{"categories":1281},[109],{"categories":1283},[],{"categories":1285},[103],{"categories":1287},[117],{"categories":1289},[103],{"categories":1291},[103],{"categories":1293},[103],{"categories":1295},[117],{"categories":1297},[103],{"categories":1299},[103],{"categories":1301},[216],{"categories":1303},[103],{"categories":1305},[404],{"categories":1307},[103],{"categories":1309},[114],{"categories":1311},[103],{"categories":1313},[103],{"categories":1315},[103],{"categories":1317},[103],{"categories":1319},[189],{"categories":1321},[114],{"categories":1323},[],{"categories":1325},[114],{"categories":1327},[],{"categories":1329},[251],{"categories":1331},[126],{"categories":1333},[],{"categories":1335},[455],{"categories":1337},[103],{"categories":1339},[114],{"categories":1341},[103],{"categories":1343},[189,103],{"categories":1345},[106],{"categories":1347},[],{"categories":1349},[103],{"categories":1351},[106],{"categories":1353},[1354],"Medical Imaging & Radiology",{"categories":1356},[189],{"categories":1358},[114],{"categories":1360},[126],{"categories":1362},[],{"categories":1364},[103],{"categories":1366},[103],{"categories":1368},[103],{"categories":1370},[],{"categories":1372},[],{"categories":1374},[103],{"categories":1376},[404],{"categories":1378},[103],{"categories":1380},[106],{"categories":1382},[103],{"categories":1384},[103],{"categories":1386},[],{"categories":1388},[114],{"categories":1390},[103],{"categories":1392},[117],{"categories":1394},[126],{"categories":1396},[103],{"categories":1398},[404],{"categories":1400},[103],{"categories":1402},[114],{"categories":1404},[103],{"categories":1406},[189],{"categories":1408},[114],{"categories":1410},[251],{"categories":1412},[189],{"categories":1414},[109],{"categories":1416},[114],{"categories":1418},[103],{"categories":1420},[103],{"categories":1422},[103],{"categories":1424},[103],{"categories":1426},[103],{"categories":1428},[114],{"categories":1430},[126],{"categories":1432},[103],{"categories":1434},[117],{"categories":1436},[],{"categories":1438},[148],{"categories":1440},[],{"categories":1442},[117],{"categories":1444},[114],{"categories":1446},[1060],{"categories":1448},[1060],{"categories":1450},[189],{"categories":1452},[103],{"categories":1454},[103],{"categories":1456},[114],{"categories":1458},[126],{"categories":1460},[189],{"categories":1462},[114],{"categories":1464},[148],{"categories":1466},[],{"categories":1468},[103],{"categories":1470},[],{"categories":1472},[103],{"categories":1474},[103],{"categories":1476},[103],{"categories":1478},[114],{"categories":1480},[1481],"Contract Review & E-Discovery",{"categories":1483},[189],{"categories":1485},[103],{"categories":1487},[106],{"categories":1489},[148],{"categories":1491},[103],{"categories":1493},[103],{"categories":1495},[216],{"categories":1497},[126],{"categories":1499},[103],{"categories":1501},[103],{"categories":1503},[114],{"categories":1505},[114],{"categories":1507},[772],{"categories":1509},[114],{"categories":1511},[114],{"categories":1513},[103],{"categories":1515},[103],{"categories":1517},[114],{"categories":1519},[103],{"categories":1521},[404],{"categories":1523},[385],{"categories":1525},[103],{"categories":1527},[114],{"categories":1529},[103],{"categories":1531},[1532],"Law-Firm Practice & Adoption",{"categories":1534},[103],{"categories":1536},[114],{"categories":1538},[189],{"categories":1540},[103],{"categories":1542},[103],{"categories":1544},[],{"categories":1546},[],{"categories":1548},[126],{"categories":1550},[],{"categories":1552},[114],{"categories":1554},[106],{"categories":1556},[251],{"categories":1558},[103],{"categories":1560},[],{"categories":1562},[106],{"categories":1564},[109],{"categories":1566},[103],{"categories":1568},[216],{"categories":1570},[],{"categories":1572},[109],{"categories":1574},[109],{"categories":1576},[],{"categories":1578},[103],{"categories":1580},[103],{"categories":1582},[126],{"categories":1584},[],{"categories":1586},[],{"categories":1588},[],{"categories":1590},[],{"categories":1592},[103],{"categories":1594},[114],{"categories":1596},[251],{"categories":1598},[103],{"categories":1600},[106],{"categories":1602},[126],{"categories":1604},[103],{"categories":1606},[103],{"categories":1608},[126],{"categories":1610},[117],{"categories":1612},[103],{"categories":1614},[795],{"categories":1616},[103],{"categories":1618},[216],{"categories":1620},[126],{"categories":1622},[109],{"categories":1624},[103],{"categories":1626},[103],{"categories":1628},[189],{"categories":1630},[103],{"categories":1632},[103],{"categories":1634},[103],{"categories":1636},[114],{"categories":1638},[103,106],{"categories":1640},[404],{"categories":1642},[103],{"categories":1644},[103],{"categories":1646},[126],{"categories":1648},[126],{"categories":1650},[189],{"categories":1652},[114],{"categories":1654},[126],{"categories":1656},[103],{"categories":1658},[103],{"categories":1660},[],{"categories":1662},[],{"categories":1664},[103],{"categories":1666},[],{"categories":1668},[103],{"categories":1670},[126],{"categories":1672},[68],{"categories":1674},[148],{"categories":1676},[189],{"categories":1678},[103],{"categories":1680},[103],{"categories":1682},[126],{"categories":1684},[],{"categories":1686},[114],{"categories":1688},[103],{"categories":1690},[103],{"categories":1692},[103],{"categories":1694},[103],{"categories":1696},[],{"categories":1698},[114],{"categories":1700},[103],{"categories":1702},[103],{"categories":1704},[],{"categories":1706},[114],{"categories":1708},[103],{"categories":1710},[103],{"categories":1712},[109],{"categories":1714},[103],{"categories":1716},[],{"categories":1718},[106],{"categories":1720},[103],{"categories":1722},[189],{"categories":1724},[126],{"categories":1726},[103],{"categories":1728},[106],{"categories":1730},[103],{"categories":1732},[126],{"categories":1734},[216],{"categories":1736},[114],{"categories":1738},[114],{"categories":1740},[103,189],{"categories":1742},[103],{"categories":1744},[148],{"categories":1746},[103],{"categories":1748},[148],{"categories":1750},[114],{"categories":1752},[189],{"categories":1754},[],{"categories":1756},[126],{"categories":1758},[251],{"categories":1760},[189],{"categories":1762},[126],{"categories":1764},[103],{"categories":1766},[117],{"categories":1768},[103],{"categories":1770},[114],{"categories":1772},[],{"categories":1774},[],{"categories":1776},[103],{"categories":1778},[],{"categories":1780},[],{"categories":1782},[117],{"categories":1784},[126],{"categories":1786},[103],{"categories":1788},[114],{"categories":1790},[114],{"categories":1792},[109],{"categories":1794},[114],{"categories":1796},[251],{"categories":1798},[103],{"categories":1800},[103],{"categories":1802},[137],{"categories":1804},[103],{"categories":1806},[103],{"categories":1808},[114],{"categories":1810},[103],{"categories":1812},[103],{"categories":1814},[358],{"categories":1816},[772],{"categories":1818},[],{"categories":1820},[189],{"categories":1822},[1532],{"categories":1824},[126],{"categories":1826},[],{"categories":1828},[],{"categories":1830},[114],{"categories":1832},[],{"categories":1834},[],{"categories":1836},[216],{"categories":1838},[103],{"categories":1840},[216],{"categories":1842},[114],{"categories":1844},[103],{"categories":1846},[126],{"categories":1848},[117],{"categories":1850},[],{"categories":1852},[103],{"categories":1854},[103],{"categories":1856},[126],{"categories":1858},[1481],{"categories":1860},[189],{"categories":1862},[189],{"categories":1864},[103],{"categories":1866},[114],{"categories":1868},[106],{"categories":1870},[103],{"categories":1872},[103],{"categories":1874},[103],{"categories":1876},[189],{"categories":1878},[189],{"categories":1880},[114],{"categories":1882},[114],{"categories":1884},[103],{"categories":1886},[103],{"categories":1888},[],{"categories":1890},[103],{"categories":1892},[],{"categories":1894},[1895],"Interaction & Product Design",{"categories":1897},[103],{"categories":1899},[114],{"categories":1901},[278],{"categories":1903},[148],{"categories":1905},[126],{"categories":1907},[103],{"categories":1909},[103],{"categories":1911},[126],{"categories":1913},[106],{"categories":1915},[114],{"categories":1917},[103],{"categories":1919},[],{"categories":1921},[114],{"categories":1923},[114],{"categories":1925},[],{"categories":1927},[126],{"categories":1929},[103],{"categories":1931},[106],{"categories":1933},[1895],{"categories":1935},[103],{"categories":1937},[106],{"categories":1939},[106],{"categories":1941},[],{"categories":1943},[126],{"categories":1945},[],{"categories":1947},[114],{"categories":1949},[148],{"categories":1951},[103],{"categories":1953},[114],{"categories":1955},[103],{"categories":1957},[114],{"categories":1959},[103],{"categories":1961},[103],{"categories":1963},[148],{"categories":1965},[68],{"categories":1967},[103],{"categories":1969},[117],{"categories":1971},[126],{"categories":1973},[1974],"Coding Agents & Dev Productivity",{"categories":1976},[148],{"categories":1978},[189],{"categories":1980},[103],{"categories":1982},[],{"categories":1984},[103],{"categories":1986},[772],{"categories":1988},[],{"categories":1990},[103],{"categories":1992},[103],{"categories":1994},[148],{"categories":1996},[],{"categories":1998},[],{"categories":2000},[103],{"categories":2002},[],{"categories":2004},[114],{"categories":2006},[103],{"categories":2008},[],{"categories":2010},[126],{"categories":2012},[126],{"categories":2014},[103],{"categories":2016},[68],{"categories":2018},[],{"categories":2020},[103],{"categories":2022},[103],{"categories":2024},[103],{"categories":2026},[68],{"categories":2028},[126],{"categories":2030},[],{"categories":2032},[],{"categories":2034},[103],{"categories":2036},[103],{"categories":2038},[114],{"categories":2040},[114],{"categories":2042},[337],{"categories":2044},[126],{"categories":2046},[126],{"categories":2048},[114],{"categories":2050},[148],{"categories":2052},[148],{"categories":2054},[114],{"categories":2056},[114],{"categories":2058},[103],{"categories":2060},[106],{"categories":2062},[1895],{"categories":2064},[103,251],{"categories":2066},[],{"categories":2068},[189],{"categories":2070},[126],{"categories":2072},[106],{"categories":2074},[103],{"categories":2076},[114],{"categories":2078},[2079],"The Designer's Role & Craft",{"categories":2081},[189],{"categories":2083},[],{"categories":2085},[114],{"categories":2087},[103],{"categories":2089},[114],{"categories":2091},[114],{"categories":2093},[103],{"categories":2095},[216],{"categories":2097},[103],{"categories":2099},[126],{"categories":2101},[189],{"categories":2103},[103],{"categories":2105},[],{"categories":2107},[114],{"categories":2109},[189],{"categories":2111},[103],{"categories":2113},[103],{"categories":2115},[2116],"AI UX Patterns",{"categories":2118},[114],{"categories":2120},[114],{"categories":2122},[114],{"categories":2124},[114],{"categories":2126},[216],{"categories":2128},[68],{"categories":2130},[103],{"categories":2132},[114],{"categories":2134},[103],{"categories":2136},[1060],{"categories":2138},[],{"categories":2140},[216],{"categories":2142},[114],{"categories":2144},[148],{"categories":2146},[126],{"categories":2148},[103],{"categories":2150},[114],{"categories":2152},[],{"categories":2154},[],{"categories":2156},[103],{"categories":2158},[114],{"categories":2160},[103],{"categories":2162},[114],{"categories":2164},[337],{"categories":2166},[189],{"categories":2168},[148],{"categories":2170},[126],{"categories":2172},[103],{"categories":2174},[114],{"categories":2176},[114],{"categories":2178},[],{"categories":2180},[103],{"categories":2182},[],{"categories":2184},[],{"categories":2186},[103],{"categories":2188},[103],{"categories":2190},[114],{"categories":2192},[126],{"categories":2194},[],{"categories":2196},[],{"categories":2198},[68],{"categories":2200},[137],{"categories":2202},[103],{"categories":2204},[68],{"categories":2206},[148],{"categories":2208},[103],{"categories":2210},[103],{"categories":2212},[114],{"categories":2214},[103],{"categories":2216},[114],{"categories":2218},[103],{"categories":2220},[103],{"categories":2222},[114],{"categories":2224},[],{"categories":2226},[],{"categories":2228},[103],{"categories":2230},[251],{"categories":2232},[103],{"categories":2234},[],{"categories":2236},[],{"categories":2238},[189],{"categories":2240},[795],{"categories":2242},[114],{"categories":2244},[106],{"categories":2246},[2079],{"categories":2248},[],{"categories":2250},[],{"categories":2252},[103],{"categories":2254},[],{"categories":2256},[],{"categories":2258},[126],{"categories":2260},[148],{"categories":2262},[216],{"categories":2264},[109],{"categories":2266},[103],{"categories":2268},[103],{"categories":2270},[109],{"categories":2272},[],{"categories":2274},[189],{"categories":2276},[103],{"categories":2278},[103],{"categories":2280},[114],{"categories":2282},[109],{"categories":2284},[103],{"categories":2286},[103],{"categories":2288},[106],{"categories":2290},[103],{"categories":2292},[],{"categories":2294},[106],{"categories":2296},[103],{"categories":2298},[216],{"categories":2300},[114],{"categories":2302},[148],{"categories":2304},[103],{"categories":2306},[109],{"categories":2308},[103],{"categories":2310},[103],{"categories":2312},[103],{"categories":2314},[114],{"categories":2316},[],{"categories":2318},[103],{"categories":2320},[126],{"categories":2322},[106],{"categories":2324},[103],{"categories":2326},[103],{"categories":2328},[],{"categories":2330},[103],{"categories":2332},[404],{"categories":2334},[148],{"categories":2336},[103],{"categories":2338},[103],{"categories":2340},[],{"categories":2342},[109],{"categories":2344},[109],{"categories":2346},[103],{"categories":2348},[103],{"categories":2350},[117],{"categories":2352},[103],{"categories":2354},[103],{"categories":2356},[103],{"categories":2358},[126],{"categories":2360},[126],{"categories":2362},[103],{"categories":2364},[],{"categories":2366},[126],{"categories":2368},[103],{"categories":2370},[126],{"categories":2372},[491],{"categories":2374},[],{"categories":2376},[],{"categories":2378},[103],{"categories":2380},[148],{"categories":2382},[],{"categories":2384},[251],{"categories":2386},[103],{"categories":2388},[103],{"categories":2390},[189],{"categories":2392},[761],{"categories":2394},[],{"categories":2396},[103],{"categories":2398},[103],{"categories":2400},[103],{"categories":2402},[126],{"categories":2404},[103],{"categories":2406},[103],{"categories":2408},[103,251],{"categories":2410},[103],{"categories":2412},[103],{"categories":2414},[189],{"categories":2416},[114],{"categories":2418},[],{"categories":2420},[114],{"categories":2422},[114],{"categories":2424},[103],{"categories":2426},[103],{"categories":2428},[103],{"categories":2430},[68],{"categories":2432},[103],{"categories":2434},[2116],{"categories":2436},[106],{"categories":2438},[68],{"categories":2440},[106],{"categories":2442},[126],{"categories":2444},[189],{"categories":2446},[114],{"categories":2448},[103],{"categories":2450},[],{"categories":2452},[103],{"categories":2454},[103],{"categories":2456},[148],{"categories":2458},[103],{"categories":2460},[114],{"categories":2462},[103],{"categories":2464},[103],{"categories":2466},[109],{"categories":2468},[],{"categories":2470},[251],{"categories":2472},[103],{"categories":2474},[337],{"categories":2476},[189],{"categories":2478},[189],{"categories":2480},[126],{"categories":2482},[114],{"categories":2484},[103],{"categories":2486},[109],{"categories":2488},[148],{"categories":2490},[103],{"categories":2492},[189],{"categories":2494},[114],{"categories":2496},[103],{"categories":2498},[103],{"categories":2500},[455],{"categories":2502},[],{"categories":2504},[103],{"categories":2506},[103],{"categories":2508},[103],{"categories":2510},[],{"categories":2512},[],{"categories":2514},[103],{"categories":2516},[103],{"categories":2518},[103],{"categories":2520},[103],{"categories":2522},[126],{"categories":2524},[103],{"categories":2526},[103],{"categories":2528},[114],{"categories":2530},[103],{"categories":2532},[103],{"categories":2534},[103],{"categories":2536},[103],{"categories":2538},[103],{"categories":2540},[],{"categories":2542},[126],{"categories":2544},[68],{"categories":2546},[103],{"categories":2548},[114],{"categories":2550},[103],{"categories":2552},[],{"categories":2554},[],{"categories":2556},[103],{"categories":2558},[103],{"categories":2560},[103],{"categories":2562},[148],{"categories":2564},[],{"categories":2566},[103],{"categories":2568},[189],{"categories":2570},[103],{"categories":2572},[251],{"categories":2574},[1532],{"categories":2576},[148],{"categories":2578},[126],{"categories":2580},[126],{"categories":2582},[126],{"categories":2584},[148],{"categories":2586},[148],{"categories":2588},[251],{"categories":2590},[],{"categories":2592},[148],{"categories":2594},[103],{"categories":2596},[106],{"categories":2598},[126],{"categories":2600},[103],{"categories":2602},[148],{"categories":2604},[],{"categories":2606},[103],{"categories":2608},[126],{"categories":2610},[126],{"categories":2612},[68],{"categories":2614},[103],{"categories":2616},[148],{"categories":2618},[103],{"categories":2620},[126],{"categories":2622},[114],{"categories":2624},[148],{"categories":2626},[114],{"categories":2628},[251],{"categories":2630},[114],{"categories":2632},[103],{"categories":2634},[103],{"categories":2636},[126],{"categories":2638},[103],{"categories":2640},[],{"categories":2642},[109],{"categories":2644},[126],{"categories":2646},[],{"categories":2648},[],{"categories":2650},[103],{"categories":2652},[114],{"categories":2654},[103],{"categories":2656},[2657],"Frameworks & Tooling",{"categories":2659},[103],{"categories":2661},[103],{"categories":2663},[126],{"categories":2665},[103],{"categories":2667},[103],{"categories":2669},[],{"categories":2671},[68],{"categories":2673},[68],{"categories":2675},[106],{"categories":2677},[114],{"categories":2679},[189],{"categories":2681},[],{"categories":2683},[1532],{"categories":2685},[103],{"categories":2687},[126],{"categories":2689},[103],{"categories":2691},[251],{"categories":2693},[251],{"categories":2695},[],{"categories":2697},[114],{"categories":2699},[148],{"categories":2701},[148],{"categories":2703},[103],{"categories":2705},[114],{"categories":2707},[],{"categories":2709},[189],{"categories":2711},[103],{"categories":2713},[103],{"categories":2715},[],{"categories":2717},[103],{"categories":2719},[103],{"categories":2721},[],{"categories":2723},[126],{"categories":2725},[103],{"categories":2727},[126],{"categories":2729},[251],{"categories":2731},[103],{"categories":2733},[126],{"categories":2735},[109],{"categories":2737},[103],{"categories":2739},[1532],{"categories":2741},[],{"categories":2743},[114],{"categories":2745},[106],{"categories":2747},[106],{"categories":2749},[],{"categories":2751},[114],{"categories":2753},[103],{"categories":2755},[2756],"AI Design Tooling",{"categories":2758},[189],{"categories":2760},[103],{"categories":2762},[103],{"categories":2764},[126],{"categories":2766},[189],{"categories":2768},[103],{"categories":2770},[126],{"categories":2772},[148],{"categories":2774},[117],{"categories":2776},[126],{"categories":2778},[103],{"categories":2780},[114],{"categories":2782},[],{"categories":2784},[103],{"categories":2786},[103],{"categories":2788},[114],{"categories":2790},[103],{"categories":2792},[103],{"categories":2794},[103],{"categories":2796},[],{"categories":2798},[114],{"categories":2800},[2657],{"categories":2802},[103],{"categories":2804},[114],{"categories":2806},[114],{"categories":2808},[126],{"categories":2810},[126],{"categories":2812},[],{"categories":2814},[126],{"categories":2816},[103],{"categories":2818},[103],{"categories":2820},[114],{"categories":2822},[109],{"categories":2824},[103],{"categories":2826},[],{"categories":2828},[103],{"categories":2830},[103],{"categories":2832},[1895],{"categories":2834},[],{"categories":2836},[103],{"categories":2838},[103],{"categories":2840},[103],{"categories":2842},[],{"categories":2844},[103],{"categories":2846},[103],{"categories":2848},[103],{"categories":2850},[216],{"categories":2852},[148],{"categories":2854},[103],{"categories":2856},[103],{"categories":2858},[1532],{"categories":2860},[106],{"categories":2862},[103],{"categories":2864},[103],{"categories":2866},[68],{"categories":2868},[103],{"categories":2870},[148],{"categories":2872},[114],{"categories":2874},[],{"categories":2876},[103],{"categories":2878},[103],{"categories":2880},[189],{"categories":2882},[103],{"categories":2884},[216],{"categories":2886},[103],{"categories":2888},[114],{"categories":2890},[],{"categories":2892},[],{"categories":2894},[],{"categories":2896},[106],{"categories":2898},[148],{"categories":2900},[114],{"categories":2902},[103],{"categories":2904},[103],{"categories":2906},[103],{"categories":2908},[358],{"categories":2910},[189],{"categories":2912},[114],{"categories":2914},[103],{"categories":2916},[],{"categories":2918},[114],{"categories":2920},[114],{"categories":2922},[],{"categories":2924},[103],{"categories":2926},[114],{"categories":2928},[103],{"categories":2930},[],{"categories":2932},[103],{"categories":2934},[103],{"categories":2936},[148],{"categories":2938},[189],{"categories":2940},[114],{"categories":2942},[189],{"categories":2944},[114],{"categories":2946},[103],{"categories":2948},[109],{"categories":2950},[],{"categories":2952},[],{"categories":2954},[103],{"categories":2956},[103],{"categories":2958},[106],{"categories":2960},[114],{"categories":2962},[148],{"categories":2964},[],{"categories":2966},[189],{"categories":2968},[],{"categories":2970},[126],{"categories":2972},[103],{"categories":2974},[126],{"categories":2976},[189],{"categories":2978},[126],{"categories":2980},[103],{"categories":2982},[],{"categories":2984},[103],{"categories":2986},[103],{"categories":2988},[],{"categories":2990},[103],{"categories":2992},[216],{"categories":2994},[103],{"categories":2996},[251],{"categories":2998},[126],{"categories":3000},[],{"categories":3002},[114],{"categories":3004},[103],{"categories":3006},[106],{"categories":3008},[455],{"categories":3010},[103],{"categories":3012},[114],{"categories":3014},[114],{"categories":3016},[103],{"categories":3018},[103],{"categories":3020},[],{"categories":3022},[103],{"categories":3024},[106],{"categories":3026},[103],{"categories":3028},[109],{"categories":3030},[126],{"categories":3032},[189],{"categories":3034},[],{"categories":3036},[],{"categories":3038},[],{"categories":3040},[114],{"categories":3042},[126],{"categories":3044},[189],{"categories":3046},[148],{"categories":3048},[103],{"categories":3050},[148],{"categories":3052},[114],{"categories":3054},[189],{"categories":3056},[103],{"categories":3058},[],{"categories":3060},[103],{"categories":3062},[137],{"categories":3064},[114],{"categories":3066},[189],{"categories":3068},[148],{"categories":3070},[109],{"categories":3072},[126],{"categories":3074},[103],{"categories":3076},[103],{"categories":3078},[148],{"categories":3080},[216],{"categories":3082},[],{"categories":3084},[],{"categories":3086},[68],{"categories":3088},[404],{"categories":3090},[103],{"categories":3092},[114],{"categories":3094},[103,126],{"categories":3096},[148],{"categories":3098},[103],{"categories":3100},[103],{"categories":3102},[103],{"categories":3104},[103],{"categories":3106},[114],{"categories":3108},[103],{"categories":3110},[114],{"categories":3112},[103],{"categories":3114},[103],{"categories":3116},[],{"categories":3118},[103],{"categories":3120},[1060],{"categories":3122},[126],{"categories":3124},[189],{"categories":3126},[103],{"categories":3128},[103],{"categories":3130},[103],{"categories":3132},[68],{"categories":3134},[114],{"categories":3136},[216],{"categories":3138},[251],{"categories":3140},[],{"categories":3142},[103],{"categories":3144},[109],{"categories":3146},[114],{"categories":3148},[106],{"categories":3150},[114],{"categories":3152},[103],{"categories":3154},[114],{"categories":3156},[117],{"categories":3158},[126],{"categories":3160},[103],{"categories":3162},[103],{"categories":3164},[],{"categories":3166},[],{"categories":3168},[],{"categories":3170},[251],{"categories":3172},[103],{"categories":3174},[148],{"categories":3176},[103],{"categories":3178},[103],{"categories":3180},[103],{"categories":3182},[103],{"categories":3184},[],{"categories":3186},[68],{"categories":3188},[109],{"categories":3190},[114],{"categories":3192},[103],{"categories":3194},[],{"categories":3196},[103],{"categories":3198},[114],{"categories":3200},[103],{"categories":3202},[251],{"categories":3204},[],{"categories":3206},[189],{"categories":3208},[189],{"categories":3210},[],{"categories":3212},[126],{"categories":3214},[103],{"categories":3216},[189],{"categories":3218},[103],{"categories":3220},[109],{"categories":3222},[114],{"categories":3224},[103],{"categories":3226},[],{"categories":3228},[148],{"categories":3230},[103],{"categories":3232},[103],{"categories":3234},[103],{"categories":3236},[189],{"categories":3238},[114],{"categories":3240},[148],{"categories":3242},[],{"categories":3244},[114],{"categories":3246},[109],{"categories":3248},[114],{"categories":3250},[189],{"categories":3252},[103],{"categories":3254},[103],{"categories":3256},[103],{"categories":3258},[404],{"categories":3260},[103],{"categories":3262},[],{"categories":3264},[103],{"categories":3266},[103],{"categories":3268},[251],{"categories":3270},[148],{"categories":3272},[68],{"categories":3274},[491],{"categories":3276},[68],{"categories":3278},[103],{"categories":3280},[],{"categories":3282},[],{"categories":3284},[],{"categories":3286},[114],{"categories":3288},[114],{"categories":3290},[126],{"categories":3292},[103],{"categories":3294},[385],{"categories":3296},[126],{"categories":3298},[103],{"categories":3300},[103],{"categories":3302},[103],{"categories":3304},[103],{"categories":3306},[114],{"categories":3308},[],{"categories":3310},[],{"categories":3312},[103],{"categories":3314},[],{"categories":3316},[103],{"categories":3318},[114],{"categories":3320},[189],{"categories":3322},[103],{"categories":3324},[103],{"categories":3326},[],{"categories":3328},[114],{"categories":3330},[117],{"categories":3332},[103],{"categories":3334},[189],{"categories":3336},[103],{"categories":3338},[114],{"categories":3340},[109],{"categories":3342},[103],{"categories":3344},[216],{"categories":3346},[114],{"categories":3348},[103],{"categories":3350},[761],{"categories":3352},[103],{"categories":3354},[114],{"categories":3356},[103],{"categories":3358},[126],{"categories":3360},[103],{"categories":3362},[455],{"categories":3364},[189],{"categories":3366},[],{"categories":3368},[148],{"categories":3370},[404],{"categories":3372},[114],{"categories":3374},[103],{"categories":3376},[],{"categories":3378},[148],{"categories":3380},[337],{"categories":3382},[114],{"categories":3384},[114],{"categories":3386},[103],{"categories":3388},[103],{"categories":3390},[114],{"categories":3392},[],{"categories":3394},[103],{"categories":3396},[109],{"categories":3398},[114],{"categories":3400},[],{"categories":3402},[126],{"categories":3404},[103],{"categories":3406},[103],{"categories":3408},[106],{"categories":3410},[148],{"categories":3412},[251],{"categories":3414},[137],{"categories":3416},[114],{"categories":3418},[114],{"categories":3420},[103],{"categories":3422},[114],{"categories":3424},[103],{"categories":3426},[106],{"categories":3428},[],{"categories":3430},[103],{"categories":3432},[103],{"categories":3434},[103],{"categories":3436},[],{"categories":3438},[],{"categories":3440},[189],{"categories":3442},[114],{"categories":3444},[103,109],{"categories":3446},[114],{"categories":3448},[103],{"categories":3450},[],{"categories":3452},[106],{"categories":3454},[68],{"categories":3456},[109],{"categories":3458},[103],{"categories":3460},[126],{"categories":3462},[103],{"categories":3464},[114],{"categories":3466},[103],{"categories":3468},[103],{"categories":3470},[103],{"categories":3472},[148],{"categories":3474},[1060],{"categories":3476},[114],{"categories":3478},[103],{"categories":3480},[],{"categories":3482},[],{"categories":3484},[103],{"categories":3486},[114],{"categories":3488},[103],{"categories":3490},[103],{"categories":3492},[251],{"categories":3494},[],{"categories":3496},[103],{"categories":3498},[114],{"categories":3500},[137],{"categories":3502},[114],{"categories":3504},[404],{"categories":3506},[],{"categories":3508},[358],{"categories":3510},[114],{"categories":3512},[103],{"categories":3514},[216],{"categories":3516},[103],{"categories":3518},[68],{"categories":3520},[114],{"categories":3522},[103],{"categories":3524},[404],{"categories":3526},[103],{"categories":3528},[251],{"categories":3530},[],{"categories":3532},[103],{"categories":3534},[216],{"categories":3536},[189],{"categories":3538},[103],{"categories":3540},[103],{"categories":3542},[103],{"categories":3544},[],{"categories":3546},[216],{"categories":3548},[148],{"categories":3550},[103],{"categories":3552},[103],{"categories":3554},[491],{"categories":3556},[106],{"categories":3558},[103],{"categories":3560},[],{"categories":3562},[],{"categories":3564},[189],{"categories":3566},[103],{"categories":3568},[68],{"categories":3570},[216],{"categories":3572},[114],{"categories":3574},[216],{"categories":3576},[148],{"categories":3578},[],{"categories":3580},[103],{"categories":3582},[103],{"categories":3584},[],{"categories":3586},[103],{"categories":3588},[103],{"categories":3590},[514],{"categories":3592},[103],{"categories":3594},[103],{"categories":3596},[114],{"categories":3598},[126],{"categories":3600},[404],{"categories":3602},[103],{"categories":3604},[103],{"categories":3606},[103],{"categories":3608},[],{"categories":3610},[103,126],{"categories":3612},[148],{"categories":3614},[114],{"categories":3616},[126],{"categories":3618},[114],{"categories":3620},[795],{"categories":3622},[126],{"categories":3624},[103],{"categories":3626},[106],{"categories":3628},[],{"categories":3630},[],{"categories":3632},[114],{"categories":3634},[103],{"categories":3636},[126],{"categories":3638},[103],{"categories":3640},[106],{"categories":3642},[126],{"categories":3644},[126],{"categories":3646},[103],{"categories":3648},[216],{"categories":3650},[103],{"categories":3652},[126],{"categories":3654},[103],{"categories":3656},[],{"categories":3658},[103],{"categories":3660},[189,103],{"categories":3662},[251],{"categories":3664},[106],{"categories":3666},[],{"categories":3668},[103],{"categories":3670},[103],{"categories":3672},[109],{"categories":3674},[109],{"categories":3676},[103],{"categories":3678},[103],{"categories":3680},[337],{"categories":3682},[103],{"categories":3684},[126],{"categories":3686},[68],{"categories":3688},[114],{"categories":3690},[126],{"categories":3692},[103],{"categories":3694},[103],{"categories":3696},[148],{"categories":3698},[216],{"categories":3700},[189],{"categories":3702},[103],{"categories":3704},[103],{"categories":3706},[103],{"categories":3708},[103],{"categories":3710},[106],{"categories":3712},[103],{"categories":3714},[114],{"categories":3716},[114],{"categories":3718},[126],{"categories":3720},[148],{"categories":3722},[126],{"categories":3724},[126],{"categories":3726},[103],{"categories":3728},[],{"categories":3730},[],{"categories":3732},[68],{"categories":3734},[103],{"categories":3736},[126],{"categories":3738},[103],{"categories":3740},[189],{"categories":3742},[404],{"categories":3744},[358],{"categories":3746},[337],{"categories":3748},[103],{"categories":3750},[103],{"categories":3752},[103],{"categories":3754},[68],{"categories":3756},[103],{"categories":3758},[103],{"categories":3760},[103],{"categories":3762},[103],{"categories":3764},[103],{"categories":3766},[103],{"categories":3768},[114],{"categories":3770},[106],{"categories":3772},[114],{"categories":3774},[103,109],{"categories":3776},[],{"categories":3778},[189],{"categories":3780},[],{"categories":3782},[117],{"categories":3784},[103],{"categories":3786},[148],{"categories":3788},[106],{"categories":3790},[106],{"categories":3792},[114],{"categories":3794},[114],{"categories":3796},[114],{"categories":3798},[103],{"categories":3800},[103],{"categories":3802},[109],{"categories":3804},[114],{"categories":3806},[126],{"categories":3808},[216],{"categories":3810},[103],{"categories":3812},[],{"categories":3814},[148],{"categories":3816},[103],{"categories":3818},[103],{"categories":3820},[103],{"categories":3822},[103],{"categories":3824},[103],{"categories":3826},[126],{"categories":3828},[148],{"categories":3830},[126],{"categories":3832},[126],{"categories":3834},[103],{"categories":3836},[103],{"categories":3838},[103],{"categories":3840},[358],{"categories":3842},[103],{"categories":3844},[114],{"categories":3846},[148],{"categories":3848},[103],{"categories":3850},[103],{"categories":3852},[103],{"categories":3854},[114],{"categories":3856},[103],{"categories":3858},[103],{"categories":3860},[103],{"categories":3862},[2657],{"categories":3864},[3865],"Clinical AI",{"categories":3867},[189],{"categories":3869},[103],{"categories":3871},[103],{"categories":3873},[103],{"categories":3875},[251],{"categories":3877},[2116],{"categories":3879},[103],{"categories":3881},[117],{"categories":3883},[103],{"categories":3885},[114],{"categories":3887},[103],{"categories":3889},[103],{"categories":3891},[148],{"categories":3893},[103],{"categories":3895},[114],{"categories":3897},[126],{"categories":3899},[216],{"categories":3901},[103],{"categories":3903},[103],{"categories":3905},[109],{"categories":3907},[103],{"categories":3909},[103],{"categories":3911},[455],{"categories":3913},[103],{"categories":3915},[],{"categories":3917},[103],{"categories":3919},[126],{"categories":3921},[106],{"categories":3923},[103],{"categories":3925},[],{"categories":3927},[],{"categories":3929},[103],{"categories":3931},[],{"categories":3933},[109],{"categories":3935},[103],{"categories":3937},[114],{"categories":3939},[148],{"categories":3941},[148],{"categories":3943},[148],{"categories":3945},[148],{"categories":3947},[],{"categories":3949},[106],{"categories":3951},[114],{"categories":3953},[148],{"categories":3955},[103],{"categories":3957},[514],{"categories":3959},[117],{"categories":3961},[103],{"categories":3963},[106],{"categories":3965},[114],{"categories":3967},[103],{"categories":3969},[103],{"categories":3971},[103,114],{"categories":3973},[114],{"categories":3975},[251],{"categories":3977},[148],{"categories":3979},[114],{"categories":3981},[148],{"categories":3983},[114],{"categories":3985},[103],{"categories":3987},[],{"categories":3989},[148],{"categories":3991},[216],{"categories":3993},[106],{"categories":3995},[103],{"categories":3997},[103],{"categories":3999},[],{"categories":4001},[126],{"categories":4003},[],{"categories":4005},[106],{"categories":4007},[114],{"categories":4009},[148],{"categories":4011},[103],{"categories":4013},[148],{"categories":4015},[106],{"categories":4017},[148],{"categories":4019},[148],{"categories":4021},[],{"categories":4023},[109],{"categories":4025},[114],{"categories":4027},[148],{"categories":4029},[148],{"categories":4031},[148],{"categories":4033},[148],{"categories":4035},[148],{"categories":4037},[148],{"categories":4039},[148],{"categories":4041},[148],{"categories":4043},[148],{"categories":4045},[148],{"categories":4047},[68],{"categories":4049},[106],{"categories":4051},[103],{"categories":4053},[103],{"categories":4055},[114],{"categories":4057},[114],{"categories":4059},[],{"categories":4061},[103,106],{"categories":4063},[],{"categories":4065},[114],{"categories":4067},[103],{"categories":4069},[148],{"categories":4071},[114],{"categories":4073},[795],{"categories":4075},[103],{"categories":4077},[103],{"categories":4079},[103],{"categories":4081},[103],{"categories":4083},[103],{"categories":4085},[337],{"categories":4087},[103],{"categories":4089},[114],{"categories":4091},[109],{"categories":4093},[114],{"categories":4095},[114],{"categories":4097},[],{"categories":4099},[114],{"categories":4101},[189],{"categories":4103},[148],{"categories":4105},[103],{"categories":4107},[],{"categories":4109},[117],{"categories":4111},[],{"categories":4113},[126],{"categories":4115},[114],{"categories":4117},[189],{"categories":4119},[103],{"categories":4121},[],{"categories":4123},[103],{"categories":4125},[],{"categories":4127},[216],{"categories":4129},[103],{"categories":4131},[],{"categories":4133},[],{"categories":4135},[148],{"categories":4137},[106],{"categories":4139},[103],{"categories":4141},[103],{"categories":4143},[109],{"categories":4145},[103],{"categories":4147},[103],{"categories":4149},[103],{"categories":4151},[109],{"categories":4153},[189],{"categories":4155},[],{"categories":4157},[103],{"categories":4159},[148],{"categories":4161},[],{"categories":4163},[103],{"categories":4165},[103],{"categories":4167},[189],{"categories":4169},[103],{"categories":4171},[216],{"categories":4173},[103],{"categories":4175},[251],{"categories":4177},[],{"categories":4179},[114],{"categories":4181},[216],{"categories":4183},[126],{"categories":4185},[],{"categories":4187},[103],{"categories":4189},[],{"categories":4191},[114],{"categories":4193},[189],{"categories":4195},[126],{"categories":4197},[],{"categories":4199},[2657],{"categories":4201},[109],{"categories":4203},[106],{"categories":4205},[103],{"categories":4207},[68],{"categories":4209},[114],{"categories":4211},[189],{"categories":4213},[126],{"categories":4215},[],{"categories":4217},[],{"categories":4219},[103],{"categories":4221},[106],{"categories":4223},[103],{"categories":4225},[216],{"categories":4227},[],{"categories":4229},[114],{"categories":4231},[114],{"categories":4233},[103],{"categories":4235},[114],{"categories":4237},[103],{"categories":4239},[148],{"categories":4241},[126],{"categories":4243},[103],{"categories":4245},[114],{"categories":4247},[117],{"categories":4249},[103],{"categories":4251},[103],{"categories":4253},[114],{"categories":4255},[103],{"categories":4257},[117],{"categories":4259},[216],{"categories":4261},[148],{"categories":4263},[],{"categories":4265},[216],{"categories":4267},[],{"categories":4269},[126],{"categories":4271},[114],{"categories":4273},[],{"categories":4275},[103],{"categories":4277},[103],{"categories":4279},[103],{"categories":4281},[103],{"categories":4283},[114],{"categories":4285},[109],{"categories":4287},[106],{"categories":4289},[103],{"categories":4291},[189],{"categories":4293},[126],{"categories":4295},[126],{"categories":4297},[103],{"categories":4299},[68],{"categories":4301},[114],{"categories":4303},[103],{"categories":4305},[103],{"categories":4307},[114],{"categories":4309},[103],{"categories":4311},[109],{"categories":4313},[189],{"categories":4315},[126],{"categories":4317},[114],{"categories":4319},[103],{"categories":4321},[117],{"categories":4323},[103],{"categories":4325},[114],{"categories":4327},[103],{"categories":4329},[148],{"categories":4331},[],{"categories":4333},[106],{"categories":4335},[103],{"categories":4337},[103],{"categories":4339},[103],{"categories":4341},[126],{"categories":4343},[126],{"categories":4345},[103],{"categories":4347},[126],{"categories":4349},[103],{"categories":4351},[114],{"categories":4353},[103],{"categories":4355},[103],{"categories":4357},[103],{"categories":4359},[103],{"categories":4361},[],{"categories":4363},[103],{"categories":4365},[189],{"categories":4367},[109],{"categories":4369},[148],{"categories":4371},[114],{"categories":4373},[103],{"categories":4375},[103],{"categories":4377},[189],{"categories":4379},[114],{"categories":4381},[103],{"categories":4383},[216],{"categories":4385},[103],{"categories":4387},[68],{"categories":4389},[103],{"categories":4391},[103],{"categories":4393},[148],{"categories":4395},[103],{"categories":4397},[103],{"categories":4399},[103],{"categories":4401},[114],{"categories":4403},[251],{"categories":4405},[103],{"categories":4407},[126],{"categories":4409},[114],{"categories":4411},[68],{"categories":4413},[],{"categories":4415},[114],{"categories":4417},[126],{"categories":4419},[103],{"categories":4421},[1974],{"categories":4423},[189],{"categories":4425},[278],{"categories":4427},[103],{"categories":4429},[103],{"categories":4431},[106],{"categories":4433},[126],{"categories":4435},[109],{"categories":4437},[126],{"categories":4439},[103],{"categories":4441},[],{"categories":4443},[114],{"categories":4445},[114],{"categories":4447},[103],{"categories":4449},[103],{"categories":4451},[68],{"categories":4453},[],{"categories":4455},[148],{"categories":4457},[],{"categories":4459},[148],{"categories":4461},[103],{"categories":4463},[103],{"categories":4465},[114],{"categories":4467},[103],{"categories":4469},[114],{"categories":4471},[114],{"categories":4473},[],{"categories":4475},[148],{"categories":4477},[103],{"categories":4479},[],{"categories":4481},[103],{"categories":4483},[103],{"categories":4485},[],{"categories":4487},[189],{"categories":4489},[126],{"categories":4491},[114],{"categories":4493},[103],{"categories":4495},[103],{"categories":4497},[216],{"categories":4499},[103],{"categories":4501},[103],{"categories":4503},[103],{"categories":4505},[106],{"categories":4507},[103],{"categories":4509},[],{"categories":4511},[103],{"categories":4513},[103],{"categories":4515},[],{"categories":4517},[106],{"categories":4519},[148],{"categories":4521},[126],{"categories":4523},[117],{"categories":4525},[404],{"categories":4527},[103],{"categories":4529},[103],{"categories":4531},[103],{"categories":4533},[126],{"categories":4535},[148],{"categories":4537},[189],{"categories":4539},[103],{"categories":4541},[103],{"categories":4543},[103],{"categories":4545},[148],{"categories":4547},[189],{"categories":4549},[103],{"categories":4551},[103],{"categories":4553},[148],{"categories":4555},[189],{"categories":4557},[103],{"categories":4559},[148],{"categories":4561},[114],{"categories":4563},[114],{"categories":4565},[114],{"categories":4567},[126],{"categories":4569},[148],{"categories":4571},[114],{"categories":4573},[114],{"categories":4575},[103],{"categories":4577},[126],{"categories":4579},[189],{"categories":4581},[103],{"categories":4583},[103],{"categories":4585},[],{"categories":4587},[114],{"categories":4589},[],{"categories":4591},[103],{"categories":4593},[],{"categories":4595},[],{"categories":4597},[114],{"categories":4599},[109],{"categories":4601},[114],{"categories":4603},[4604],"Liability & Ethics",{"categories":4606},[103],{"categories":4608},[114],{"categories":4610},[106],{"categories":4612},[114],{"categories":4614},[109],{"categories":4616},[216],{"categories":4618},[114],{"categories":4620},[],{"categories":4622},[491],{"categories":4624},[114],{"categories":4626},[],{"categories":4628},[106],{"categories":4630},[114],{"categories":4632},[],{"categories":4634},[114],{"categories":4636},[103],{"categories":4638},[103],{"categories":4640},[148],{"categories":4642},[103],{"categories":4644},[103],{"categories":4646},[114],{"categories":4648},[103],{"categories":4650},[103],{"categories":4652},[103],{"categories":4654},[148],{"categories":4656},[114],{"categories":4658},[126],{"categories":4660},[189],{"categories":4662},[106],{"categories":4664},[103],{"categories":4666},[103],{"categories":4668},[],{"categories":4670},[114],{"categories":4672},[114],{"categories":4674},[404],{"categories":4676},[189],{"categories":4678},[251],{"categories":4680},[148],{"categories":4682},[103],{"categories":4684},[189],{"categories":4686},[103],{"categories":4688},[106],{"categories":4690},[],{"categories":4692},[114],{"categories":4694},[103],{"categories":4696},[103],{"categories":4698},[114],{"categories":4700},[103],{"categories":4702},[189],{"categories":4704},[],{"categories":4706},[114],{"categories":4708},[117],{"categories":4710},[148],{"categories":4712},[114],{"categories":4714},[109],{"categories":4716},[],{"categories":4718},[103],{"categories":4720},[117],{"categories":4722},[103],{"categories":4724},[114],{"categories":4726},[148],{"categories":4728},[106],{"categories":4730},[251],{"categories":4732},[103],{"categories":4734},[103],{"categories":4736},[103],{"categories":4738},[148],{"categories":4740},[109],{"categories":4742},[103],{"categories":4744},[189],{"categories":4746},[148],{"categories":4748},[251],{"categories":4750},[103],{"categories":4752},[114],{"categories":4754},[],{"categories":4756},[455],{"categories":4758},[],{"categories":4760},[103],{"categories":4762},[251],{"categories":4764},[68],{"categories":4766},[114],{"categories":4768},[114],{"categories":4770},[4771],"Design News & Tools",{"categories":4773},[103],{"categories":4775},[148],{"categories":4777},[103],{"categories":4779},[103],{"categories":4781},[106],{"categories":4783},[103],{"categories":4785},[189],{"categories":4787},[114],{"categories":4789},[114],{"categories":4791},[189],{"categories":4793},[103],{"categories":4795},[404],{"categories":4797},[103],{"categories":4799},[103],{"categories":4801},[404],{"categories":4803},[103],{"categories":4805},[216],{"categories":4807},[103],{"categories":4809},[114],{"categories":4811},[],{"categories":4813},[103],{"categories":4815},[103],{"categories":4817},[103],{"categories":4819},[148],{"categories":4821},[106],{"categories":4823},[],{"categories":4825},[103],{"categories":4827},[103],{"categories":4829},[126],{"categories":4831},[514],{"categories":4833},[126],{"categories":4835},[189],{"categories":4837},[103],{"categories":4839},[103,114],{"categories":4841},[216,109],{"categories":4843},[103],{"categories":4845},[103],{"categories":4847},[103],{"categories":4849},[],{"categories":4851},[114],{"categories":4853},[],{"categories":4855},[126],{"categories":4857},[103],{"categories":4859},[126],{"categories":4861},[],{"categories":4863},[114],{"categories":4865},[103],{"categories":4867},[148],{"categories":4869},[103],{"categories":4871},[],{"categories":4873},[114],{"categories":4875},[103],{"categories":4877},[],{"categories":4879},[189],{"categories":4881},[103],{"categories":4883},[114],{"categories":4885},[103],{"categories":4887},[103],{"categories":4889},[106],{"categories":4891},[114],{"categories":4893},[103],{"categories":4895},[],{"categories":4897},[251],{"categories":4899},[216],{"categories":4901},[109],{"categories":4903},[109],{"categories":4905},[103],{"categories":4907},[106],{"categories":4909},[106],{"categories":4911},[103],{"categories":4913},[114],{"categories":4915},[103],{"categories":4917},[103],{"categories":4919},[103],{"categories":4921},[126],{"categories":4923},[103],{"categories":4925},[106],{"categories":4927},[114],{"categories":4929},[103],{"categories":4931},[216],{"categories":4933},[103],{"categories":4935},[148],{"categories":4937},[103],{"categories":4939},[103],{"categories":4941},[114],{"categories":4943},[103],{"categories":4945},[],{"categories":4947},[126],{"categories":4949},[],{"categories":4951},[126],{"categories":4953},[114],{"categories":4955},[106],{"categories":4957},[],{"categories":4959},[68],{"categories":4961},[251],{"categories":4963},[103],{"categories":4965},[126],{"categories":4967},[103],{"categories":4969},[],{"categories":4971},[148],{"categories":4973},[114],{"categories":4975},[126],{"categories":4977},[189],{"categories":4979},[103],{"categories":4981},[103],{"categories":4983},[114],{"categories":4985},[126],{"categories":4987},[114],{"categories":4989},[148],{"categories":4991},[103],{"categories":4993},[117],{"categories":4995},[106],{"categories":4997},[117],{"categories":4999},[148],{"categories":5001},[126],{"categories":5003},[103],{"categories":5005},[189],{"categories":5007},[109],{"categories":5009},[103],{"categories":5011},[103],{"categories":5013},[103],{"categories":5015},[103],{"categories":5017},[103],{"categories":5019},[114],{"categories":5021},[103],{"categories":5023},[114],{"categories":5025},[103],{"categories":5027},[103],{"categories":5029},[106],{"categories":5031},[103],{"categories":5033},[114],{"categories":5035},[114],{"categories":5037},[189],{"categories":5039},[114],{"categories":5041},[114],{"categories":5043},[106],{"categories":5045},[114],{"categories":5047},[189],{"categories":5049},[],{"categories":5051},[103],{"categories":5053},[68],{"categories":5055},[404],{"categories":5057},[103],{"categories":5059},[103],{"categories":5061},[103],{"categories":5063},[126],{"categories":5065},[103],{"categories":5067},[],{"categories":5069},[114],{"categories":5071},[216],{"categories":5073},[103],{"categories":5075},[148],{"categories":5077},[114],{"categories":5079},[103],{"categories":5081},[216],{"categories":5083},[114],{"categories":5085},[109],{"categories":5087},[109],{"categories":5089},[103],{"categories":5091},[103],{"categories":5093},[103],{"categories":5095},[106],{"categories":5097},[],{"categories":5099},[103],{"categories":5101},[103],{"categories":5103},[114],{"categories":5105},[114],{"categories":5107},[103],{"categories":5109},[103],{"categories":5111},[103],{"categories":5113},[126],{"categories":5115},[],{"categories":5117},[106],{"categories":5119},[103],{"categories":5121},[103],{"categories":5123},[114],{"categories":5125},[114],{"categories":5127},[],{"categories":5129},[126],{"categories":5131},[126],{"categories":5133},[103],{"categories":5135},[216],{"categories":5137},[109],{"categories":5139},[189],{"categories":5141},[],{"categories":5143},[103],{"categories":5145},[114],{"categories":5147},[106],{"categories":5149},[103],{"categories":5151},[126],{"categories":5153},[106],{"categories":5155},[148],{"categories":5157},[68],{"categories":5159},[148],{"categories":5161},[114],{"categories":5163},[],{"categories":5165},[148],{"categories":5167},[114],{"categories":5169},[189],{"categories":5171},[68],{"categories":5173},[103],{"categories":5175},[],{"categories":5177},[114],{"categories":5179},[114],{"categories":5181},[2657],{"categories":5183},[148],{"categories":5185},[126],{"categories":5187},[103],{"categories":5189},[103],{"categories":5191},[103],{"categories":5193},[103],{"categories":5195},[109],{"categories":5197},[103],{"categories":5199},[106],{"categories":5201},[1532],{"categories":5203},[251],{"categories":5205},[106],{"categories":5207},[],{"categories":5209},[],{"categories":5211},[148],{"categories":5213},[114],{"categories":5215},[103],{"categories":5217},[148],{"categories":5219},[],{"categories":5221},[114],{"categories":5223},[114],{"categories":5225},[114],{"categories":5227},[],{"categories":5229},[103],{"categories":5231},[],{"categories":5233},[148],{"categories":5235},[106],{"categories":5237},[189],{"categories":5239},[103],{"categories":5241},[114],{"categories":5243},[148],{"categories":5245},[103],{"categories":5247},[148],{"categories":5249},[],{"categories":5251},[148],{"categories":5253},[106],{"categories":5255},[404],{"categories":5257},[114],{"categories":5259},[103],{"categories":5261},[],{"categories":5263},[126],{"categories":5265},[114],{"categories":5267},[117],{"categories":5269},[114],{"categories":5271},[106],{"categories":5273},[],{"categories":5275},[],{"categories":5277},[],{"categories":5279},[189],{"categories":5281},[114],{"categories":5283},[103],{"categories":5285},[103],{"categories":5287},[],{"categories":5289},[],{"categories":5291},[],{"categories":5293},[189],{"categories":5295},[103],{"categories":5297},[],{"categories":5299},[114],{"categories":5301},[103],{"categories":5303},[106],{"categories":5305},[],{"categories":5307},[],{"categories":5309},[189],{"categories":5311},[103],{"categories":5313},[148],{"categories":5315},[],{"categories":5317},[216],{"categories":5319},[148],{"categories":5321},[216],{"categories":5323},[68],{"categories":5325},[103],{"categories":5327},[103],{"categories":5329},[],{"categories":5331},[],{"categories":5333},[114],{"categories":5335},[],{"categories":5337},[103],{"categories":5339},[404],{"categories":5341},[103],{"categories":5343},[103],{"categories":5345},[103],{"categories":5347},[103],{"categories":5349},[],{"categories":5351},[114],{"categories":5353},[103],{"categories":5355},[103],{"categories":5357},[],{"categories":5359},[114],{"categories":5361},[103],{"categories":5363},[148],{"categories":5365},[103],{"categories":5367},[216],{"categories":5369},[109],{"categories":5371},[103],{"categories":5373},[103],{"categories":5375},[114],{"categories":5377},[68],{"categories":5379},[114],{"categories":5381},[114],{"categories":5383},[],{"categories":5385},[114],{"categories":5387},[],{"categories":5389},[103],{"categories":5391},[],{"categories":5393},[148],{"categories":5395},[109],{"categories":5397},[],{"categories":5399},[103],{"categories":5401},[],{"categories":5403},[189],{"categories":5405},[106],{"categories":5407},[],{"categories":5409},[109],{"categories":5411},[216],{"categories":5413},[103],{"categories":5415},[126],{"categories":5417},[106],{"categories":5419},[68],{"categories":5421},[109],{"categories":5423},[126],{"categories":5425},[114],{"categories":5427},[126],{"categories":5429},[],{"categories":5431},[117],{"categories":5433},[103],{"categories":5435},[],{"categories":5437},[114],{"categories":5439},[106],{"categories":5441},[189],{"categories":5443},[103],{"categories":5445},[106],{"categories":5447},[114],{"categories":5449},[251],{"categories":5451},[103],{"categories":5453},[103],{"categories":5455},[103],{"categories":5457},[106],{"categories":5459},[68],{"categories":5461},[114],{"categories":5463},[],{"categories":5465},[103],{"categories":5467},[103],{"categories":5469},[126],{"categories":5471},[114],{"categories":5473},[148],{"categories":5475},[126],{"categories":5477},[103],{"categories":5479},[117],{"categories":5481},[],{"categories":5483},[189],{"categories":5485},[148],{"categories":5487},[106],{"categories":5489},[114],{"categories":5491},[103],{"categories":5493},[103],{"categories":5495},[114],{"categories":5497},[117],{"categories":5499},[103],{"categories":5501},[114],{"categories":5503},[103],{"categories":5505},[109],{"categories":5507},[114],{"categories":5509},[114,251],{"categories":5511},[103],{"categories":5513},[103],{"categories":5515},[114],{"categories":5517},[126],{"categories":5519},[103],{"categories":5521},[103],{"categories":5523},[68],{"categories":5525},[114],{"categories":5527},[216],{"categories":5529},[114],{"categories":5531},[109],{"categories":5533},[],{"categories":5535},[114],{"categories":5537},[103],{"categories":5539},[109],{"categories":5541},[],{"categories":5543},[],{"categories":5545},[126],{"categories":5547},[103],{"categories":5549},[103],{"categories":5551},[114],{"categories":5553},[68],{"categories":5555},[216],{"categories":5557},[103],{"categories":5559},[103],{"categories":5561},[114],{"categories":5563},[],{"categories":5565},[114],{"categories":5567},[148],{"categories":5569},[114],{"categories":5571},[],{"categories":5573},[148],{"categories":5575},[126],{"categories":5577},[2657],{"categories":5579},[106],{"categories":5581},[126],{"categories":5583},[103],{"categories":5585},[114],{"categories":5587},[103],{"categories":5589},[103],{"categories":5591},[216],{"categories":5593},[126],{"categories":5595},[],{"categories":5597},[148],{"categories":5599},[103],{"categories":5601},[],{"categories":5603},[114],{"categories":5605},[103],{"categories":5607},[103],{"categories":5609},[103],{"categories":5611},[103],{"categories":5613},[114],{"categories":5615},[103],{"categories":5617},[103],{"categories":5619},[117],{"categories":5621},[103],{"categories":5623},[114],{"categories":5625},[103],{"categories":5627},[103],{"categories":5629},[103],{"categories":5631},[103],{"categories":5633},[103],{"categories":5635},[103],{"categories":5637},[109],{"categories":5639},[],{"categories":5641},[117],{"categories":5643},[148],{"categories":5645},[114],{"categories":5647},[103],{"categories":5649},[126],{"categories":5651},[],{"categories":5653},[126],{"categories":5655},[126],{"categories":5657},[114],{"categories":5659},[126],{"categories":5661},[103],{"categories":5663},[103],{"categories":5665},[103],{"categories":5667},[114],{"categories":5669},[126],{"categories":5671},[103],{"categories":5673},[103],{"categories":5675},[114],{"categories":5677},[148],{"categories":5679},[103],{"categories":5681},[103],{"categories":5683},[103],{"categories":5685},[109],{"categories":5687},[103],{"categories":5689},[114],{"categories":5691},[189],{"categories":5693},[],{"categories":5695},[103],{"categories":5697},[68],{"categories":5699},[114],{"categories":5701},[103],{"categories":5703},[103],{"categories":5705},[],{"categories":5707},[103],{"categories":5709},[103],{"categories":5711},[148],{"categories":5713},[103],{"categories":5715},[103],{"categories":5717},[114],{"categories":5719},[216],{"categories":5721},[],{"categories":5723},[],{"categories":5725},[126],{"categories":5727},[103],{"categories":5729},[148],{"categories":5731},[126],{"categories":5733},[148],{"categories":5735},[103],{"categories":5737},[216],{"categories":5739},[68],{"categories":5741},[103],{"categories":5743},[106],{"categories":5745},[114],{"categories":5747},[103],{"categories":5749},[114],{"categories":5751},[114],{"categories":5753},[103],{"categories":5755},[109],{"categories":5757},[],{"categories":5759},[68],{"categories":5761},[103],{"categories":5763},[],{"categories":5765},[148],{"categories":5767},[103],{"categories":5769},[68],{"categories":5771},[103],{"categories":5773},[126],{"categories":5775},[126],{"categories":5777},[126],{"categories":5779},[114],{"categories":5781},[114],{"categories":5783},[114],{"categories":5785},[103],{"categories":5787},[103],{"categories":5789},[189],{"categories":5791},[68],{"categories":5793},[68],{"categories":5795},[],{"categories":5797},[148],{"categories":5799},[103],{"categories":5801},[103],{"categories":5803},[126],{"categories":5805},[],{"categories":5807},[148],{"categories":5809},[148],{"categories":5811},[148],{"categories":5813},[],{"categories":5815},[114],{"categories":5817},[103],{"categories":5819},[],{"categories":5821},[106],{"categories":5823},[109],{"categories":5825},[],{"categories":5827},[103],{"categories":5829},[103],{"categories":5831},[],{"categories":5833},[126],{"categories":5835},[],{"categories":5837},[],{"categories":5839},[],{"categories":5841},[],{"categories":5843},[103],{"categories":5845},[148],{"categories":5847},[],{"categories":5849},[],{"categories":5851},[103],{"categories":5853},[103],{"categories":5855},[103],{"categories":5857},[68],{"categories":5859},[103],{"categories":5861},[68],{"categories":5863},[],{"categories":5865},[68],{"categories":5867},[68],{"categories":5869},[251],{"categories":5871},[114],{"categories":5873},[126],{"categories":5875},[],{"categories":5877},[],{"categories":5879},[68],{"categories":5881},[126],{"categories":5883},[126],{"categories":5885},[126],{"categories":5887},[],{"categories":5889},[106],{"categories":5891},[126],{"categories":5893},[126],{"categories":5895},[106],{"categories":5897},[126],{"categories":5899},[109],{"categories":5901},[126],{"categories":5903},[126],{"categories":5905},[126],{"categories":5907},[68],{"categories":5909},[148],{"categories":5911},[148],{"categories":5913},[103],{"categories":5915},[126],{"categories":5917},[68],{"categories":5919},[251],{"categories":5921},[68],{"categories":5923},[68],{"categories":5925},[68],{"categories":5927},[],{"categories":5929},[109],{"categories":5931},[],{"categories":5933},[251],{"categories":5935},[126],{"categories":5937},[126],{"categories":5939},[126],{"categories":5941},[114],{"categories":5943},[148,109],{"categories":5945},[68],{"categories":5947},[],{"categories":5949},[],{"categories":5951},[68],{"categories":5953},[],{"categories":5955},[68],{"categories":5957},[148],{"categories":5959},[114],{"categories":5961},[],{"categories":5963},[126],{"categories":5965},[103],{"categories":5967},[189],{"categories":5969},[],{"categories":5971},[103],{"categories":5973},[],{"categories":5975},[148],{"categories":5977},[106],{"categories":5979},[68],{"categories":5981},[],{"categories":5983},[126],{"categories":5985},[148],[5987,6061,6128,6228],{"id":5988,"title":5989,"ai":5990,"body":5996,"categories":6030,"created_at":69,"date_modified":69,"description":62,"extension":70,"faq":69,"featured":71,"kicker_label":69,"meta":6031,"navigation":84,"path":6047,"published_at":6048,"question":69,"scraped_at":6049,"seo":6050,"sitemap":6051,"source_id":6052,"source_name":6053,"source_type":91,"source_url":6054,"stem":6055,"tags":6056,"thumbnail_url":69,"tldr":6058,"tweet":69,"unknown_tags":6059,"__hash__":6060},"summaries\u002Fsummaries\u002Fc6f1bc88e627db47-parcae-stabilizes-loops-to-match-2x-transformer-qu-summary.md","Parcae Stabilizes Loops to Match 2x Transformer Quality",{"provider":7,"model":5991,"input_tokens":5992,"output_tokens":5993,"processing_time_ms":5994,"cost_usd":5995},"x-ai\u002Fgrok-4.1-fast",8134,2375,17913,0.00230745,{"type":14,"value":5997,"toc":6025},[5998,6002,6005,6008,6012,6015,6018,6022],[17,5999,6001],{"id":6000},"designing-stable-looped-architectures","Designing Stable Looped Architectures",[22,6003,6004],{},"Looped transformers route activations through a fixed block of layers T times, boosting compute without adding parameters—ideal for memory-constrained edge deployment. Parcae uses a middle-looped structure: prelude (P) embeds input to latent e; recurrent block (R) updates hidden state h_t for T loops with e injected each iteration; coda (C) outputs from final h_T. Prior looped models like RDMs fail due to residual state explosion and loss spikes from unconstrained dynamics.",[22,6006,6007],{},"Model the loop as a nonlinear dynamical system: h_{t+1} = Ā h_t + B̄ e + R̄(h_t, e). Stability requires spectral norm ρ(Ā) \u003C 1. Parcae discretizes a continuous system using zero-order hold and Euler integration with learned step Δ: Ā = exp(Δ A), B̄ = Δ B. Constrain A as diagonal with negative entries A = Diag(-exp(log A)), ensuring ρ(Ā) \u003C 1 by design—no hyperparameter tuning needed for convergence. This fixes addition-based (ρ(Ā)=1, marginal) and concatenation-projection (ρ(Ā)>1, unstable) flaws in priors.",[17,6009,6011],{"id":6010},"beating-baselines-with-parameter-efficiency","Beating Baselines with Parameter Efficiency",[22,6013,6014],{},"On Huginn, 350M Parcae drops validation perplexity 6.3% vs RDMs (10.76 to 10.09 PPL), 9.1% on WikiText, +1.8 downstream accuracy points. At 100M, 4.5% PPL gain (14.23 to 13.59). On FineWeb-Edu (104B tokens, nanochat setup), 1.3B Parcae scores 2.99 points higher on Core, 1.18 on Core-Extended than parameter-matched Transformers. Critically, 770M Parcae hits 25.07 Core—matching 1.3B Transformer's 25.45—delivering up to 87.5% of twice-sized Transformer's quality.",[22,6016,6017],{},"Looping adds an orthogonal scaling axis: isoFLOP tests at 140M\u002F370M show looped Parcae (optimal mean recurrence μ_rec) beats fixed-depth (μ_rec=1) by 1.2-2.0 Core points under same params\u002FFLOPs.",[17,6019,6021],{"id":6020},"first-scaling-laws-for-recurrence-depth","First Scaling Laws for Recurrence Depth",[22,6023,6024],{},"Optimal μ_rec scales as C^{0.40}, training tokens as C^{0.78} (C= FLOP budget), holding across scales. Test-time loop count T beyond training saturates via L(T) = L_∞ + Z e^{-z T}, plateauing near training μ_rec—setting a ceiling on extrapolation. This parametric law predicts held-out loss with 0.85-1.31% error, enabling reliable planning: train deeper loops for compute-optimal quality without memory bloat.",{"title":62,"searchDepth":63,"depth":63,"links":6026},[6027,6028,6029],{"id":6000,"depth":63,"text":6001},{"id":6010,"depth":63,"text":6011},{"id":6020,"depth":63,"text":6021},[103],{"content_references":6032,"triage":6044},[6033,6037,6041],{"type":75,"title":6034,"url":6035,"context":6036},"Parcae","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2604.12946","recommended",{"type":6038,"title":6039,"url":6040,"context":6036},"other","Parcae Model Weights","https:\u002F\u002Fhuggingface.co\u002Fcollections\u002FSandyResearch\u002Fparcae",{"type":6038,"title":6042,"url":6043,"context":6036},"Parcae Technical Details","https:\u002F\u002Fwww.together.ai\u002Fblog\u002Fparcae",{"relevance":80,"novelty":80,"quality":81,"actionability":63,"composite":6045,"reasoning":6046},3.05,"Category: AI & LLMs. The article discusses a new architecture for looped transformers, which is relevant to AI engineering, but it lacks practical applications or frameworks that the audience can directly implement. While it presents some new insights into model efficiency, it does not provide actionable steps for product builders.","\u002Fsummaries\u002Fc6f1bc88e627db47-parcae-stabilizes-loops-to-match-2x-transformer-qu-summary","2026-04-16 08:30:30","2026-04-19 01:22:43",{"title":5989,"description":62},{"loc":6047},"c6f1bc88e627db47","MarkTechPost","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F04\u002F16\u002Fucsd-and-together-ai-research-introduces-parcae-a-stable-architecture-for-looped-language-models-that-achieves-the-quality-of-a-transformer-twice-the-size\u002F","summaries\u002Fc6f1bc88e627db47-parcae-stabilizes-loops-to-match-2x-transformer-qu-summary",[6057,94,95,96],"llm","Parcae enforces looped transformer stability via negative diagonal matrices in a dynamical system, outperforming baselines and achieving 87.5% of a twice-sized Transformer's quality at half parameters.",[],"w5bUNLMbNnMepMdiskfNW1esyE0__I9nWhPLCEPtMq8",{"id":6062,"title":6063,"ai":6064,"body":6069,"categories":6098,"created_at":69,"date_modified":69,"description":62,"extension":70,"faq":69,"featured":71,"kicker_label":69,"meta":6099,"navigation":84,"path":6115,"published_at":6116,"question":69,"scraped_at":6117,"seo":6118,"sitemap":6119,"source_id":6120,"source_name":6121,"source_type":91,"source_url":6122,"stem":6123,"tags":6124,"thumbnail_url":69,"tldr":6125,"tweet":69,"unknown_tags":6126,"__hash__":6127},"summaries\u002Fsummaries\u002F0d1957d00ad6e7e2-gpu-bandwidth-limits-llm-speed-not-flops-summary.md","GPU Bandwidth Limits LLM Speed, Not FLOPS",{"provider":7,"model":5991,"input_tokens":6065,"output_tokens":6066,"processing_time_ms":6067,"cost_usd":6068},8371,1988,22871,0.00264555,{"type":14,"value":6070,"toc":6094},[6071,6075,6078,6081,6084,6088,6091],[17,6072,6074],{"id":6073},"throughput-design-hides-latency-with-massive-parallelism","Throughput Design Hides Latency with Massive Parallelism",[22,6076,6077],{},"GPUs prioritize throughput over single-thread latency by allocating transistors to thousands of execution units and a large register file rather than branch predictors or deep caches. A single GPU thread is slower than a CPU core (~1ns instruction), but 20,000+ run concurrently. Off-chip HBM access takes 700+ cycles on H100, so GPUs hide this by keeping enough independent warps ready—switching when one stalls. This requires high occupancy: ratio of resident warps to max (64 per H100 SM). Low occupancy from high register use (e.g., 128 regs\u002Fthread limits to 512 threads\u002FSM or 16 warps, 25% occupancy) starves the scheduler, collapsing throughput despite saturated Tensor Cores.",[22,6079,6080],{},"Threads group into 32-thread warps as the scheduling unit under SIMT: hardware issues one instruction across the warp while tracking per-thread PCs and registers for independent appearance. Pre-Volta lockstep caused deadlocks on intra-warp sync; Volta+ Independent Thread Scheduling (ITS) dynamically regroups converging threads, enabling mutexes without divergence penalties (though divergence still serializes paths, doubling time on 50\u002F50 if\u002Felse). H100 SMs (132 total) divide into 4 quadrants, each with warp scheduler, 16k registers, 32 FP32\u002F16 INT32 cores, 1 Tensor Core, and L0 instr cache. Blocks (CTAs) run on one SM for shared mem sync; Hopper clusters co-schedule blocks across GPCs for DSMEM (7x faster than global mem).",[22,6082,6083],{},"Warp divergence hurts irregular data (e.g., padding branches); fix via specialization—e.g., FlashAttention-3 assigns producer warps for loads, consumers for math, zero divergence, overlapping mem\u002Fcompute. Little’s Law quantifies: in-flight warps = throughput × latency. For 400-cycle HBM loads at 1 instr\u002Fcycle, need 400+ warps to sustain SM utilization; fewer drops throughput to 25%.",[17,6085,6087],{"id":6086},"six-tier-memory-hierarchy-sets-bandwidth-bounds","Six-Tier Memory Hierarchy Sets Bandwidth Bounds",[22,6089,6090],{},"Data tiers trade capacity\u002Fbandwidth\u002Flatency: registers (256KB\u002FSM, 65k 32-bit, 1-cycle) > shared\u002FL1 (228KB shared max, 30-40 cycles) > L2 (50MB, 258-743 cycles) > HBM3 (80GB, 3.35TB\u002Fs, 700+ cycles) > NVLink (900GB\u002Fs\u002FGPU, µs) > NVMe. Keep working set close: high regs\u002Fthread (>255) spills to HBM local mem, killing loops. Shared mem tiles inputs for reuse (GEMM loads slab once, computes multiple times). L1 coalesces warp loads (base+i patterns >> strided). L2 absorbs weight re-reads; >50MB spills to HBM.",[22,6092,6093],{},"LLM decode exemplifies: 70B FP16 model needs 140GB\u002Ftoken read (42ms at 3.35TB\u002Fs pre-compute), one FLOP\u002Fbyte. Bandwidth binds because arithmetic intensity (FLOPs\u002Fbyte) is ~1; roofline (part 2) shows compute underutilized without high reuse. HBM holds weights\u002FKV\u002Factivations; misses from upper tiers thrash it. NVLink shards large models (e.g., tensor parallel syncs partials), but frequent comm bottlenecks vs. pipeline parallel (activations\u002Flayer).",{"title":62,"searchDepth":63,"depth":63,"links":6095},[6096,6097],{"id":6073,"depth":63,"text":6074},{"id":6086,"depth":63,"text":6087},[103],{"content_references":6100,"triage":6113},[6101,6105,6109],{"type":75,"title":6102,"author":6103,"context":6104},"FlashAttention-3","Shah et al.","cited",{"type":75,"title":6106,"author":6107,"publisher":6108,"context":6104},"Microbenchmarks of the Hopper architecture","Luo et al.","2025",{"type":6038,"title":6110,"author":6111,"context":6112},"NVIDIA’s Hopper architecture documentation","NVIDIA","mentioned",{"relevance":80,"novelty":80,"quality":81,"actionability":63,"composite":6045,"reasoning":6114},"Category: AI & LLMs. The article discusses GPU architecture and its implications for LLM performance, which is relevant to AI product builders. However, while it provides insights into GPU memory bandwidth, it lacks concrete actionable steps for implementing this knowledge in product development.","\u002Fsummaries\u002F0d1957d00ad6e7e2-gpu-bandwidth-limits-llm-speed-not-flops-summary","2026-05-06 02:50:10","2026-05-06 16:13:45",{"title":6063,"description":62},{"loc":6115},"0d1957d00ad6e7e2","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Fwarps-memory-hierarchy-and-why-bandwidth-beats-flops-how-gpus-actually-work-part-1-06170834ad33?source=rss----98111c9905da---4","summaries\u002F0d1957d00ad6e7e2-gpu-bandwidth-limits-llm-speed-not-flops-summary",[94,95],"Generating one token from a 70B model on H100 needs 140GB weight reads—one op per byte—making memory bandwidth the inference bottleneck, not compute throughput.",[],"OXBz1imk9itxNT8ySnee4POT_2AlsDS3zHL4klRnIMo",{"id":6129,"title":6130,"ai":6131,"body":6136,"categories":6215,"created_at":69,"date_modified":69,"description":62,"extension":70,"faq":69,"featured":71,"kicker_label":69,"meta":6216,"navigation":84,"path":6217,"published_at":6218,"question":69,"scraped_at":69,"seo":6219,"sitemap":6220,"source_id":6221,"source_name":6121,"source_type":91,"source_url":6222,"stem":6223,"tags":6224,"thumbnail_url":69,"tldr":6225,"tweet":69,"unknown_tags":6226,"__hash__":6227},"summaries\u002Fsummaries\u002Fword2vec-turning-word-neighborhoods-into-embedding-summary.md","Word2Vec: Turning Word Neighborhoods into Embeddings",{"provider":7,"model":5991,"input_tokens":6132,"output_tokens":6133,"processing_time_ms":6134,"cost_usd":6135},8588,1873,21956,0.0026316,{"type":14,"value":6137,"toc":6209},[6138,6142,6158,6161,6165,6172,6175,6186,6190,6193,6196,6199,6203,6206],[17,6139,6141],{"id":6140},"shift-from-isolated-ids-to-relational-embeddings","Shift from Isolated IDs to Relational Embeddings",[22,6143,6144,6145,6149,6150,6153,6154,6157],{},"Before Word2Vec, words were treated as unique IDs or one-hot vectors (e.g., cat → ",[6146,6147,6148],"span",{},"1,0,0,0,0","), preserving identity but ignoring relationships like 'cat' closer to 'dog' than 'engine'. Word2Vec flips this by learning dense vectors where meaning emerges from context: a word's vector is shaped by its repeated local neighborhoods in text. For a tiny corpus ('the cat drinks milk', 'the dog drinks water'), 'cat' appears near 'the', 'drinks', 'milk', 'chases', 'mouse', while 'dog' shares 'the', 'drinks', 'chases' but differs on 'water', 'ball'. Similar contexts deliver matching gradient signals during training, pulling vectors like cat ",[6146,6151,6152],{},"0.82, 0.21, -0.05"," and dog ",[6146,6155,6156],{},"0.79, 0.25, -0.03"," into nearby regions, enabling geometric analogies like king - man + woman ≈ queen.",[22,6159,6160],{},"This relational view—words as positions in a space preserving structure—outperforms sparse representations because similar training pressures from neighborhoods create clustered embeddings without explicit semantic rules.",[17,6162,6164],{"id":6163},"cbow-vs-skip-gram-dual-paths-to-context-prediction","CBOW vs Skip-gram: Dual Paths to Context Prediction",[22,6166,6167,6168,6171],{},"Word2Vec optimizes dense vectors (e.g., size 3 for vocab of 9) via a simple network: one-hot input (size 9) → hidden layer (size 3) → output scores (size 9). The hidden weights form the embedding table, where each word's row (e.g., initial cat ",[6146,6169,6170],{},"0.11, -0.08, 0.05",") gets refined.",[22,6173,6174],{},"CBOW predicts center from context (input: 'the', 'drinks' → target: 'cat'), treating surroundings as clues that constrain word identity, like recovering a word from its situational fit. Skip-gram reverses it (input: 'cat' → targets: 'the', 'drinks'), capturing a word's relational footprint—what neighbors it generates. With window size 1, Skip-gram generates pairs like cat → the, cat → drinks; CBOW inverts them.",[22,6176,6177,6178,6181,6182,6185],{},"Both unify around mutual definition: context shapes word (CBOW), word shapes context (Skip-gram). Skip-gram excels for rare words by amplifying their signal; CBOW smooths frequent ones. Together, they force embeddings to encode predictive utility, yielding a map where milk ",[6146,6179,6180],{},"0.10, 0.88, -0.12"," clusters near water ",[6146,6183,6184],{},"0.07, 0.84, -0.10",".",[17,6187,6189],{"id":6188},"training-mechanics-gradients-sculpt-the-space","Training Mechanics: Gradients Sculpt the Space",[22,6191,6192],{},"Training slides a window over text, generating examples (e.g., center 'cat' with contexts 'the', 'drinks'). For Skip-gram on cat → the: retrieve cat's vector, compute output scores (e.g., the: 0.12 → softmax prob 0.20), measure error against target, backpropagate to nudge weights—pulling cat closer to 'the', pushing from negatives like 'engine'.",[22,6194,6195],{},"Negative sampling scales this: for cat → drinks, attract to true pair, repel 3-5 random fakes (e.g., 'banana', 'cloud'), forming geometry via affinity (pet\u002Faction contexts) and boundaries (unrelated ones). Repeated across corpus, similar contexts yield parallel updates: cat and dog, both near 'the\u002Fdrinks\u002Fchases', converge without semantic labels.",[22,6197,6198],{},"Outcome: random initials become relational map. Training builds it via 'enormous tiny corrections'; full process turns prediction errors into stable positions.",[17,6200,6202],{"id":6201},"inference-and-limitations-in-modern-context","Inference and Limitations in Modern Context",[22,6204,6205],{},"Post-training, discard the predictor; use the embedding matrix for lookups (cat's vector), similarity (cosine distance clusters cat\u002Fdog over cat\u002Fengine), averaging for sentences ('the cat drinks milk' → mean vector), or downstream tasks like classification.",[22,6207,6208],{},"Word2Vec revolutionized NLP by proving prediction yields emergent semantics, replacing hand-engineered features with learned geometry. Yet static vectors fail polysemy ('bank' as river\u002Ffinance gets one embedding), spurring contextual models like BERT. Legacy: modern LLMs inherit context-driven, relational meaning—embeddings as vectors first, structure second.",{"title":62,"searchDepth":63,"depth":63,"links":6210},[6211,6212,6213,6214],{"id":6140,"depth":63,"text":6141},{"id":6163,"depth":63,"text":6164},{"id":6188,"depth":63,"text":6189},{"id":6201,"depth":63,"text":6202},[],{},"\u002Fsummaries\u002Fword2vec-turning-word-neighborhoods-into-embedding-summary","2026-04-08 21:21:21",{"title":6130,"description":62},{"loc":6217},"2165d09f4254bef0","https:\u002F\u002Funknown","summaries\u002Fword2vec-turning-word-neighborhoods-into-embedding-summary",[94,95],"Word2Vec learns dense word vectors by predicting local contexts with CBOW or Skip-gram, clustering similar words like 'cat' and 'dog' via repeated gradient updates from shared neighborhoods.",[],"6VqxuTzkcylmMleWNUuTyJeef_Ufd7syKMvOUkR5RDE",{"id":6229,"title":6230,"ai":6231,"body":6236,"categories":6341,"created_at":69,"date_modified":69,"description":62,"extension":70,"faq":69,"featured":71,"kicker_label":69,"meta":6342,"navigation":84,"path":6343,"published_at":6344,"question":69,"scraped_at":69,"seo":6345,"sitemap":6346,"source_id":6347,"source_name":6348,"source_type":91,"source_url":6222,"stem":6349,"tags":6350,"thumbnail_url":69,"tldr":6351,"tweet":69,"unknown_tags":6352,"__hash__":6353},"summaries\u002Fsummaries\u002Fbatched-l2-norm-layer-for-torch-neural-nets-summary.md","Batched L2 Norm Layer for Torch Neural Nets",{"provider":7,"model":5991,"input_tokens":6232,"output_tokens":6233,"processing_time_ms":6234,"cost_usd":6235},4617,1235,10447,0.0015184,{"type":14,"value":6237,"toc":6336},[6238,6242,6250,6265,6269,6276,6314,6318],[17,6239,6241],{"id":6240},"core-layer-design","Core Layer Design",[22,6243,6244,6245,6249],{},"This nn.L2Normalize module processes 2D tensors (batch size n x vector dim d), normalizing each row vector to unit L2 norm (||x||_2 = 1). Use it in Torch neural nets for tasks like embedding normalization, where direction matters more than magnitude. Instantiate via ",[6246,6247,6248],"code",{},"local layer = nn.L2Normalize()",", then integrate into models like Sequential for end-to-end differentiability.",[22,6251,6252,6253,6256,6257,6260,6261,6264],{},"Forward pass (",[6246,6254,6255],{},"updateOutput","): Computes per-row L2 norms squared via elementwise square and sum over dim 2 (",[6246,6258,6259],{},"input:cmul(input):sum(2)","), takes sqrt, then elementwise divides input by expanded norms (",[6246,6262,6263],{},"input:cdiv(buffer:expandAs(input))","). Avoids loops for batch efficiency; buffers reuse across calls.",[17,6266,6268],{"id":6267},"gradient-computation","Gradient Computation",[22,6270,6271,6272,6275],{},"Backward pass (",[6246,6273,6274],{},"updateGradInput",") derives local Jacobian of L2 transform for chain rule. Key steps:",[36,6277,6278,6285,6291,6297,6303],{},[39,6279,6280,6281,6284],{},"Forms identity tensor repeated over batch (",[6246,6282,6283],{},"torch.eye(d):repeatTensor(n,1):view(n,d,d)",").",[39,6286,6287,6288,6284],{},"Scales diagonal by norm squared (",[6246,6289,6290],{},"cmul(eye, normSquared:view(n,1,1):expand(n,d,d))",[39,6292,6293,6294,6284],{},"Subtracts outer products (",[6246,6295,6296],{},"-torch.bmm(input:view(n,d,1), input:view(n,1,d))",[39,6298,6299,6300,6284],{},"Divides by cubed norms (",[6246,6301,6302],{},"cdiv(pow(buffer,3):expand(n,d,d))",[39,6304,6305,6306,6309,6310,6313],{},"Applies via batched matmul: ",[6246,6307,6308],{},"bmm(diag, gradOutput:view(n,d,1)):resize(n,d)"," (fixed with ",[6246,6311,6312],{},":squeeze()"," post-line 31).\nThis ensures correct gradients during backprop, critical for training stability in nets with normalization layers.",[17,6315,6317],{"id":6316},"implementation-notes-and-fixes","Implementation Notes and Fixes",[22,6319,6320,6321,6324,6325,6328,6329,6331,6332,6335],{},"Code uses lazy buffer init (",[6246,6322,6323],{},"self.buffer = self.buffer or input.new()",") for memory efficiency. Assumes mini-batch inputs only (errors on non-2D). Community feedback: Could swap manual norm for ",[6246,6326,6327],{},"torch.norm()"," in forward for simplicity; Karpathy confirmed feasibility. Atcold noted dimension mismatch in gradInput without ",[6246,6330,6312],{}," after bmm resize—fixed by author. Soumith (Torch maintainer) provided additional pointers (unspecified). Thin gist from 2015; modern PyTorch has ",[6246,6333,6334],{},"torch.nn.functional.normalize(p=2, dim=1)"," as built-in alternative.",{"title":62,"searchDepth":63,"depth":63,"links":6337},[6338,6339,6340],{"id":6240,"depth":63,"text":6241},{"id":6267,"depth":63,"text":6268},{"id":6316,"depth":63,"text":6317},[126],{},"\u002Fsummaries\u002Fbatched-l2-norm-layer-for-torch-neural-nets-summary","2026-04-08 21:21:20",{"title":6230,"description":62},{"loc":6343},"07bd9d1a251cebe3","Andrej Karpathy Gists","summaries\u002Fbatched-l2-norm-layer-for-torch-neural-nets-summary",[95,94],"Custom Torch nn.Module normalizes each row of n x d input tensor to unit L2 norm, with efficient batched forward\u002Fbackward passes for training.",[],"20C1Dsl0GWqJxzOXYYcvQPEK3LwoQdSQgNUb_QYBP5Q"]