筛选结果
39 篇排序
4:25:13EN → 简体中文
Lex Fridman· 2026年1月31日播客架构几乎没变，变的是数据、成本和开放权重主持 Lex FridmanNathan Lambert 和 Sebastian Raschka 带 Lex Fridman 回顾了这一年：训练方法和数据集的变化，远大于模型设计的变化。展望 2026 年，争论的焦点似乎是推理成本、智能体，以及真正开放的模型该归谁。
46:25ENLex Fridman· 2019年1月17日播客Deep Learning at the Edge of 2019: BERT, Autopilot, and the Ideas That Broke Through主持 Lex FridmanA tour of the architectural, applied, and automation breakthroughs that defined deep learning in 2018 and set up 2019.
1:29:03ENLex Fridman· 2016年9月27日播客From Word Vectors to Memory Networks: The Building Blocks of Deep NLP主持 Lex FridmanRichard Socher explains how word embeddings, recurrent models, GRUs, pointer mixtures, and dynamic memory networks turn language tasks into trainable end-to-end systems.
1:00:51ENLex Fridman播客Deep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network Foundations主持 Lex FridmanA fast, equation-level walk through feed-forward networks, backpropagation, practical training tricks, dropout and batch normalization, from the 2016 Deep Learning School.
1:07:29ENLex Fridman播客Deep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZero主持 Lex FridmanLex Fridman's MIT 6.S091 opening lecture walks from the basic RL framework through DQN, actor-critic methods and AlphaZero to the unsolved problem of moving from simulation to the real world.
9:59ENLex Fridman播客Is Language or Vision Harder? Ilya Sutskever on the Unity of Machine Learning主持 Lex FridmanIn a short clip from his 2020 conversation with Lex Fridman, Ilya Sutskever explains why vision, language and reinforcement learning share the same few principles, and why asking which problem is harder is the wrong question.
1:25:16ENLex Fridman播客From Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional Networks主持 Lex FridmanA 2016 Deep Learning School talk covering how convnets work, how the ImageNet winners evolved, and how to apply them without being a hero.
1:24:43ENLex Fridman播客From Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016主持 Lex FridmanRuslan Salakhutdinov walks through autoencoders, Boltzmann machines, variational autoencoders and adversarial networks at the Deep Learning School, with candid notes on what did and did not work.
58:46ENLex Fridman播客Caging the Neural Network: How Aptiv Thinks About Safe Self-Driving主持 Lex FridmanAptiv Autonomous Mobility's Karl Iagnemma and Oscar Beijbom explain why end-to-end learning is hard to trust in cars, and show how PointPillars and nuScenes push lidar perception forward.
1:15:59ENLex Fridman播客Steering Through Time: How Recurrent Networks and LSTMs Learn from Sequences主持 Lex FridmanLex Fridman's MIT 6.S094 lecture walks from backpropagation basics to LSTMs and the way they are used to predict steering in self-driving cars.
18:46ENLex Fridman播客Deep Learning Plus One Idea: Ilya Sutskever on Building AGI主持 Lex FridmanIn a May 2020 conversation, Sutskever discusses self-play, simulation, bodies and consciousness, tests of intelligence, and how an AGI might be governed and aligned.
37:00ENLex Fridman播客Inside the YouTube Algorithm: Related Graphs, Satisfaction Surveys and the Viewers Who Are Part of the Code主持 Lex FridmanYouTube's head of search and discovery, Cristos Goodrow, explains to Lex Fridman how search and recommendations work, which signals matter, and how the team measures whether viewers are better off.
1:31:52ENLex Fridman播客From Phonemes to CTC: How Deep Learning Rebuilt Speech Recognition主持 Lex FridmanBaidu's Adam Coates walks through the traditional speech pipeline, the CTC-based end-to-end engine that replaced much of it, and what it takes to scale and deploy it.
17:40ENLex Fridman播客From AlphaGo Zero to MuZero: How Self-Play Strips Knowledge Out of AI主持 Lex FridmanDeepMind's David Silver explains why removing human knowledge made AlphaZero stronger and more general, and how MuZero extended the idea to worlds with unknown rules.
1:07:35ENLex Fridman播客Why AI Will Never Be Perfect: Lex Fridman's Case for Keeping Humans in the Loop主持 Lex FridmanIn MIT 6.S093's opening lecture, Lex Fridman lays out five research areas of human-centered AI, from machine teaching to arguing machines that flag their own uncertainty.
16:41ENLex Fridman播客AlphaFold 2 and the Protein-Folding Breakthrough: Why Lex Fridman Calls It a Landmark for AI and Biology主持 Lex FridmanA quick explainer on DeepMind's CASP14 result, how protein folding works, how AlphaFold 1 and 2 likely differ, and what the advance could unlock.
1:19:52ENLex Fridman播客From Pixels to Steering Wheels: Convolutional Networks and End-to-End Driving主持 Lex FridmanLex Fridman's MIT 6.S094 lecture explains how convolutional neural networks work, where deep learning helps a self-driving car, and how to train a network to steer from video.
1:27:30ENLex Fridman播客From NAND Gates to Self-Driving Traffic: Deep Reinforcement Learning in One Lecture主持 Lex FridmanLex Fridman's second MIT 6.S094 lecture walks from the humble perceptron to deep Q-learning and the browser-based DeepTraffic competition.
1:05:15ENLex Fridman播客Taming the Long Tail: How Waymo Builds a Self-Driving Factory主持 Lex FridmanWaymo principal scientist Drago Anguelov explains how machine learning infrastructure, hybrid design and smart simulated agents tackle the rare events of autonomous driving.
1:27:15ENLex Fridman播客Policy Gradients vs. Q-Learning: John Schulman's Field Guide to Deep Reinforcement Learning主持 Lex FridmanOpenAI's John Schulman walks through the core methods of deep RL, from the score function estimator to TRPO and DQN, and says when each one is worth using.
1:19:21ENLex Fridman播客Vapnik's Case for Learning by Predicates, Not Just by More Data主持 Lex FridmanIn an MIT lecture, Vladimir Vapnik argues that complete statistical learning needs two mechanisms, data and invariants, and that choosing smart predicates is where intelligence lives.
1:03:25ENLex Fridman播客Theano in an Hour: Symbolic Graphs, Automatic Gradients and a Compiler That Rewrites Your Math主持 Lex FridmanPascal Lamblin of MILA walks through how Theano builds, differentiates, optimizes and runs computation graphs, then trains logistic regression, a convnet and an LSTM.
13:58ENLex Fridman播客Deep Reinforcement Learning, Explained by the Researcher Behind AlphaGo主持 Lex FridmanDavid Silver of DeepMind walks through what reinforcement learning is, how its building blocks fit together, and why deep neural networks keep surprising even the experts.
57:55ENLex Fridman播客From Q-Tables to AlphaGo Zero: A Self-Driving Car Lecture on Deep Reinforcement Learning主持 Lex FridmanLex Fridman's MIT 6.S094 lecture walks from the AI pipeline and Q-learning to deep Q-networks, AlphaGo Zero and the DeepTraffic competition.加载更多已显示 24 篇，共 39 篇