Resultados
271 artículosOrdenar
42:45EN
Lex Fridman· 16 dic 2018Pódcast · 2 vocesA one-legged robot learned a backflip from "this is better"Invitado: Pieter Abbeel · Presenta: Lex FridmanPieter Abbeel tells Lex Fridman why preference comparisons, self-play, ten-minute demos, and messy ensembles of simulators are the practical path through deep reinforcement learning.
54:03ENLex Fridman· 16 nov 2018Pódcast · 2 vocesThe Hardest Part of Learning Was Left Out of the TextbooksInvitado: Vladimir Vapnik · Presenta: Lex FridmanVladimir Vapnik tells Lex Fridman why intelligence is the work of inventing predicates that shrink the admissible set of functions, not of fitting a rule to a mountain of data.
42:18ENLex Fridman· 20 oct 2018Pódcast · 2 vocesAn Adult Can Change Last Year's Mind. A Network Still Cannot.Invitado: Yoshua Bengio · Presenta: Lex FridmanYoshua Bengio tells Lex Fridman that the missing pieces of deep learning sit in credit assignment, training objectives, and a kind of compositionality borrowed from classical AI — not in ten thousand layers.
1:29:03ENLex Fridman· 27 sept 2016PódcastFrom Word Vectors to Memory Networks: The Building Blocks of Deep NLPPresenta: 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 FridmanPódcastDeep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network FoundationsPresenta: Lex FridmanA fast, equation-level walk through feed-forward networks, backpropagation, practical training tricks, dropout and batch normalization, from the 2016 Deep Learning School.
1:56:35EN
Cognitive Revolution "How AI Changes Everything"PódcastFrom Autocomplete to Alien Optimizer: Riley Goodside on Three Eras of PromptingPresenta: Nathan LabenzScale AI's first staff prompt engineer traces how language models went from pure text prediction to instruction following to RLHF, and what that means for building with them.
1:07:29ENLex 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.
24:22ENLex FridmanPódcast · 2 vocesCraftsmanship, First Principles and the Road to Self-Driving: Jim Keller on Working with Elon MuskInvitado: Jim Keller · Presenta: Lex FridmanThe veteran chip architect explains why he thinks autonomous driving is a tractable engineering problem, how Tesla's cost constraints shaped its hardware, and what he took from Musk's way of thinking.
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.
15:01ENLex FridmanPódcast · 2 vocesDeep Learning Is a System 1 Machine: Daniel Kahneman on What AI Still LacksInvitado: Daniel Kahneman · Presenta: Lex FridmanThe Nobel-winning psychologist tells Lex Fridman how his fast-and-slow thinking framework maps onto deep learning, and why driving among pedestrians may require understanding people.
56:20EN
No Priors: AI, Machine Learning, Tech, & StartupsPódcast · 2 vocesBiohub's Bet: Building Open AI World Models of Biology From Proteins Up to CellsPresenta: Sarah Guo, Elad GilMark Zuckerberg, Priscilla Chan and Alex Rives explain why Biohub pairs a frontier AI lab with frontier wet-lab biology, and why it releases tools like ESMFold2 as open source.
1:25:16ENLex FridmanPódcastFrom Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional NetworksPresenta: 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.
1:28:53ENLex FridmanPódcast · 2 vocesMachine Learning for Business Students: Powerful, Narrow, and Easier to Fool Than You ThinkInvitado: MIT Sloan · Presenta: Lex FridmanLex Fridman's non-technical MIT Sloan lecture explains how machine learning works, why it is so capable at perception, and where it still breaks in the real world.
11:11ENLex FridmanPódcast · 2 vocesYann LeCun on Benchmarks, Interactive Environments, and Why Human Intelligence Is Not GeneralInvitado: Yann Lecun · Presenta: Lex FridmanIn a 2019 clip, LeCun defends benchmarks as a test of AI claims, explains why interactive environments break the usual train-test protocol, and argues that "general intelligence" is a misnomer.
1:24:43ENLex FridmanPódcastFrom Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016Presenta: 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.
1:17:38ENLex FridmanPódcast · 2 vocesBrains Are Body Regulators: Lisa Feldman Barrett on Why Emotions Are Constructed, Not DetectedInvitado: Lisa Feldman Barrett · Presenta: Lex FridmanIn a guest talk for MIT's AGI course, neuroscientist Lisa Feldman Barrett explains why faces don't display emotions, why brains exist to run bodies, and what that means for building human-like AI.
58:46ENLex FridmanPódcastCaging the Neural Network: How Aptiv Thinks About Safe Self-DrivingPresenta: 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.
1:23:18ENCognitive Revolution "How AI Changes Everything"PódcastFrom GPT-2 to GPT-3 Moments in Robotics: Six DeepMind Papers on Bridging Robots and the InternetPresenta: Nathan LabenzKeerthana Gopalakrishnan and Ted Xiao walk through RT-2, RT-X, RT-Trajectory, AutoRT, Learning to Learn Faster and PIVOT, and say what is still missing for general-purpose robots.
1:15:59ENLex FridmanPódcastSteering Through Time: How Recurrent Networks and LSTMs Learn from SequencesPresenta: 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.
1:03:59ENCognitive Revolution "How AI Changes Everything"PódcastBuilding a World Model of Life: Biohub's Alex Rives on Why Better Measurement Must Come Before Virtual CellsPresenta: Nathan LabenzBiohub's head of science explains why today's virtual cell models fall short, how a $1.8 billion data push aims to fix it, and what a five-year information-level model of the cell could unlock.
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.
37:00ENLex FridmanPódcastInside the YouTube Algorithm: Related Graphs, Satisfaction Surveys and the Viewers Who Are Part of the CodePresenta: 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 FridmanPódcastFrom Phonemes to CTC: How Deep Learning Rebuilt Speech RecognitionPresenta: 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 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.Cargar másMostrando 24 de 271