Résultats
88 articlesTrier
1:20:21EN
Lex Fridman· 19 janv. 2019Podcast · 2 voixEinstein Was the Worst of Five Ph.D. StudentsInvité : Tomaso Poggio · Anime : Lex FridmanMIT neuroscientist Tomaso Poggio on why intelligence is science's deepest problem, and what brains still have to teach machines.
46:25ENLex Fridman· 17 janv. 2019PodcastDeep Learning at the Edge of 2019: BERT, Autopilot, and the Ideas That Broke ThroughAnime : Lex FridmanA tour of the architectural, applied, and automation breakthroughs that defined deep learning in 2018 and set up 2019.
1:19:59ENLex Fridman· 23 déc. 2018Podcast · 2 voixSchmidhuber’s bet: true meta-learning rewrites the learner, not the last layerInvité : Juergen Schmidhuber · Anime : Lex FridmanJürgen Schmidhuber tells Lex Fridman how Gödel machines, compression-as-science, Power Play, LSTMs, and world models all descend from a teenage plan to multiply one person’s curiosity into a better physicist than he could ever be.
42:45ENLex Fridman· 16 déc. 2018Podcast · 2 voixA one-legged robot learned a backflip from "this is better"Invité : Pieter Abbeel · Anime : 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. 2018Podcast · 2 voixThe Hardest Part of Learning Was Left Out of the TextbooksInvité : Vladimir Vapnik · Anime : 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. 2018Podcast · 2 voixAn Adult Can Change Last Year's Mind. A Network Still Cannot.Invité : Yoshua Bengio · Anime : 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. 2016PodcastFrom Word Vectors to Memory Networks: The Building Blocks of Deep NLPAnime : 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 FridmanPodcastDeep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network FoundationsAnime : 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 FridmanPodcastDeep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZeroAnime : 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.
1:25:16ENLex FridmanPodcastFrom Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional NetworksAnime : 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.
54:33ENLex FridmanPodcast · 2 voixVision or Lidar, Human or Machine: Lex Fridman's 2019 Map of the Self-Driving RaceInvité : Self-Driving Cars · Anime : Lex FridmanThe opening lecture of MIT's 6.S094 course surveys 2018's milestones, the industry's optimistic predictions, and the beliefs about driving and humans that will decide who wins.
1:24:43ENLex FridmanPodcastFrom Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016Anime : 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 FridmanPodcastCaging the Neural Network: How Aptiv Thinks About Safe Self-DrivingAnime : 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 FridmanPodcastSteering Through Time: How Recurrent Networks and LSTMs Learn from SequencesAnime : 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.
1:31:52ENLex FridmanPodcastFrom Phonemes to CTC: How Deep Learning Rebuilt Speech RecognitionAnime : 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.
1:11:50ENLex FridmanPodcastData Is Everything: Teaching Self-Driving Cars to Understand the Human Behind the WheelAnime : Lex FridmanIn an MIT lecture, Lex Fridman shows how deep learning can sense pedestrians, driver posture, gaze, emotion and cognitive load, and why that matters for human-centered autonomy.
1:18:48ENLex FridmanPodcastData Movement, Not Math: How to Make Deep Learning Fit on Robots and PhonesAnime : Lex FridmanMIT professor Vivienne Sze explains why moving data dominates the energy cost of neural networks and how co-designing hardware and algorithms can cut it by orders of magnitude.
1:19:52ENLex FridmanPodcastFrom Pixels to Steering Wheels: Convolutional Networks and End-to-End DrivingAnime : 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 FridmanPodcastFrom NAND Gates to Self-Driving Traffic: Deep Reinforcement Learning in One LectureAnime : 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 FridmanPodcastTaming the Long Tail: How Waymo Builds a Self-Driving FactoryAnime : 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 FridmanPodcastPolicy Gradients vs. Q-Learning: John Schulman's Field Guide to Deep Reinforcement LearningAnime : 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 FridmanPodcastVapnik's Case for Learning by Predicates, Not Just by More DataAnime : 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 FridmanPodcastTheano in an Hour: Symbolic Graphs, Automatic Gradients and a Compiler That Rewrites Your MathAnime : 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.
1:08:06ENLex FridmanPodcast · 2 voixDeep Learning in One Lecture: From Perceptrons to AutoML and the Limits of LearningInvité : Deep Learning Basics · Anime : Lex FridmanLex Fridman's opening lecture for MIT's 6.S094 course surveys why deep learning took off, how neural networks learn, and where the technique still falls short.Charger plus24 sur 88 affichés