Canales actualizados recientemente

Elige uno para ver solo ese canalVer todos los canales →
AI Engineerhoy硅谷101ayerPragerUanteayerY CombinatoranteayerSemiAnalysishace 3 díasa16zhace 3 díasGOTO Conferenceshace 3 díasLatent Spacehace 4 díasDwarkesh Patelhace 4 díasAdrian Twaroghace 5 días

Resultados

3 artículos
Ordenar
TemaDeep LearningDuraciónMenos de 15 minVoces2 voces
10:16EN
Lex FridmanPódcast · 2 vocesReasoning Without Logic: Yann LeCun on Teaching Neural Networks to ThinkInvitado: Yann Lecun · Presenta: Lex FridmanYann LeCun explains why he believes neural networks can reason, and what memory, recurrence and continuous representations would need to look like.Modelos y entrenamientoFundamentos de MLDeep Learning+3
10:34EN
Lex FridmanPódcast · 2 vocesWhy Deep Learning Needs Rules: Chollet on Interpolation, Abstraction and Hybrid AIInvitado: François Chollet · Presenta: Lex FridmanFrançois Chollet explains why neural networks only interpolate between points they have seen, and why the best AI systems pair them with symbolic rules.Modelos y entrenamientoFundamentos de MLDeep Learning+2
11:59EN
Lex FridmanPódcast · 2 vocesFrom a Side Project to TensorFlow's Core: François Chollet on How Keras Came to BeInvitado: François Chollet · Presenta: Lex FridmanThe creator of Keras recalls why he built it in 2015 around recurrent networks, how it moved onto TensorFlow, and what TensorFlow 2.0 means for its design.Código abierto y comunidadDeep LearningOpen-source ecosystems+3