필터 결과
88개정렬
1:20:21EN
Lex Fridman· 2019년 1월 19일팟캐스트 · 2명Einstein Was the Worst of Five Ph.D. Students게스트 Tomaso Poggio · 진행자 Lex FridmanMIT neuroscientist Tomaso Poggio on why intelligence is science's deepest problem, and what brains still have to teach machines.
46:25ENLex Fridman· 2019년 1월 17일팟캐스트Deep Learning at the Edge of 2019: BERT, Autopilot, and the Ideas That Broke Through진행자 Lex FridmanA tour of the architectural, applied, and automation breakthroughs that defined deep learning in 2018 and set up 2019.
1:19:59ENLex Fridman· 2018년 12월 23일팟캐스트 · 2명Schmidhuber’s bet: true meta-learning rewrites the learner, not the last layer게스트 Juergen Schmidhuber · 진행자 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· 2018년 12월 16일팟캐스트 · 2명A one-legged robot learned a backflip from "this is better"게스트 Pieter Abbeel · 진행자 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· 2018년 11월 16일팟캐스트 · 2명The Hardest Part of Learning Was Left Out of the Textbooks게스트 Vladimir Vapnik · 진행자 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· 2018년 10월 20일팟캐스트 · 2명An Adult Can Change Last Year's Mind. A Network Still Cannot.게스트 Yoshua Bengio · 진행자 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· 2016년 9월 27일팟캐스트From Word Vectors to Memory Networks: The Building Blocks of Deep NLP진행자 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 Fridman팟캐스트Deep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network Foundations진행자 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 Fridman팟캐스트Deep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZero진행자 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 Fridman팟캐스트From Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional Networks진행자 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 Fridman팟캐스트 · 2명Vision or Lidar, Human or Machine: Lex Fridman's 2019 Map of the Self-Driving Race게스트 Self-Driving Cars · 진행자 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 Fridman팟캐스트From Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016진행자 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 Fridman팟캐스트Caging the Neural Network: How Aptiv Thinks About Safe Self-Driving진행자 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 Fridman팟캐스트Steering Through Time: How Recurrent Networks and LSTMs Learn from Sequences진행자 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 Fridman팟캐스트From Phonemes to CTC: How Deep Learning Rebuilt Speech Recognition진행자 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 Fridman팟캐스트Data Is Everything: Teaching Self-Driving Cars to Understand the Human Behind the Wheel진행자 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 Fridman팟캐스트Data Movement, Not Math: How to Make Deep Learning Fit on Robots and Phones진행자 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 Fridman팟캐스트From Pixels to Steering Wheels: Convolutional Networks and End-to-End Driving진행자 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 Fridman팟캐스트From NAND Gates to Self-Driving Traffic: Deep Reinforcement Learning in One Lecture진행자 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 Fridman팟캐스트Taming the Long Tail: How Waymo Builds a Self-Driving Factory진행자 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 Fridman팟캐스트Policy Gradients vs. Q-Learning: John Schulman's Field Guide to Deep Reinforcement Learning진행자 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 Fridman팟캐스트Vapnik's Case for Learning by Predicates, Not Just by More Data진행자 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 Fridman팟캐스트Theano in an Hour: Symbolic Graphs, Automatic Gradients and a Compiler That Rewrites Your Math진행자 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 Fridman팟캐스트 · 2명Deep Learning in One Lecture: From Perceptrons to AutoML and the Limits of Learning게스트 Deep Learning Basics · 진행자 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.더 보기88개 중 24개 표시