Resultados
90 artículosOrdenar
1:07:29EN
Lex FridmanPódcastDeep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZeroPresenta: 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 FridmanPódcastIs Language or Vision Harder? Ilya Sutskever on the Unity of Machine LearningPresenta: 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.
18:46ENLex FridmanPódcastDeep Learning Plus One Idea: Ilya Sutskever on Building AGIPresenta: 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.
17:40ENLex FridmanPódcastFrom AlphaGo Zero to MuZero: How Self-Play Strips Knowledge Out of AIPresenta: 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.
1:27:30ENLex FridmanPódcastFrom NAND Gates to Self-Driving Traffic: Deep Reinforcement Learning in One LecturePresenta: Lex FridmanLex Fridman's second MIT 6.S094 lecture walks from the humble perceptron to deep Q-learning and the browser-based DeepTraffic competition.
1:27:15ENLex FridmanPódcastPolicy Gradients vs. Q-Learning: John Schulman's Field Guide to Deep Reinforcement LearningPresenta: 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.
13:58ENLex FridmanPódcastDeep Reinforcement Learning, Explained by the Researcher Behind AlphaGoPresenta: 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 FridmanPódcastFrom Q-Tables to AlphaGo Zero: A Self-Driving Car Lecture on Deep Reinforcement LearningPresenta: 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.
1:00:15ENLex FridmanPódcast · 2 vocesCircuit Search, Hindsight and Self-Play: Ilya Sutskever's Case for Where Learning Is GoingInvitado: Ilya Sutskever · Presenta: Lex FridmanIn an MIT AGI lecture, OpenAI's co-founder explains why deep learning works, then walks through meta-learning, hindsight experience replay, sim-to-real transfer, self-play and learning goals from human feedback.
26:45ENLex FridmanPódcast · 2 vocesStart Small, Build Habits, Pick Your Team: Andrew Ng's Practical Advice for Learning Deep LearningInvitado: Andrew Ng · Presenta: Lex FridmanIn a clip from the Lex Fridman Podcast, Andrew Ng explains how to begin in deep learning, how to study effectively, and how to choose a career path.
1:31:29ENLex FridmanPódcastIs Driving More Like Chess or Conversation? Lex Fridman's Opening Lecture on Deep Learning for Self-Driving CarsPresenta: Lex FridmanThe first lecture of MIT 6.S094 introduces neural networks, reinforcement learning and computer vision through the question of how hard driving really is.
1:12:00ENLex FridmanPódcastWhy Deep Learning Works at All: Yoshua Bengio on Composition, Saddle Points and the Case for Unsupervised LearningPresenta: Lex FridmanIn a 2016 Deep Learning School talk, Yoshua Bengio explains the assumptions that let neural nets beat the curse of dimensionality and lays out the open challenges ahead.
1:02:06ENLex FridmanPódcastDeep Learning for Self-Driving Cars: Why Edge Cases and Human Nature Are the Real ProblemPresenta: Lex FridmanLex Fridman opens MIT's 6.S094 with a tour of what deep learning is, how it works, what it has achieved and where it still breaks, framed around autonomous vehicles.