絞り込み結果
83 件並び順
1:17:29EN
Lex Fridman· 2019年9月23日ポッドキャスト · 2 人The Algorithm Is Already Better. The Clinic Still Uses 1967.ゲスト Regina Barzilay · ホスト Lex FridmanMIT's Regina Barzilay on why deep learning already beats the breast-cancer 'density' score — and why data, liability, and incentives still will not move.
1:59:49ENLex Fridman· 2019年9月14日ポッドキャスト · 2 人Intelligence is not the height of a building: François Chollet on Keras, deep learning, and why AGI will not explodeゲスト François Chollet · ホスト Lex FridmanThe Keras creator tells Lex Fridman that intelligence lives in a brain, a body, and a problem, that science already is a recursively self-improving superhuman system with linear output, and that the real near-term danger is the newsfeed.
1:44:11ENLex Fridman· 2019年8月27日ポッドキャスト · 2 人A Single GPU Is Enough: Jeremy Howard on Teaching Deep Learningゲスト Jeremy Howard · ホスト Lex FridmanThe fast.ai founder tells Lex Fridman why domain experts, not more papers or more TPUs, will decide whether deep learning actually helps people.
1:10:58ENLex Fridman· 2019年6月3日ポッドキャスト · 2 人The Hadoop Lesson That Made Google Give TensorFlow Awayゲスト Rajat Monga · ホスト Lex FridmanIn November 2015, Google put its core internal machine-learning system on GitHub. Rajat Monga explains why a company of that size would hand over the hard-to-copy part.
1:46:01ENLex Fridman· 2019年4月29日ポッドキャスト · 2 人The Night AlphaStar Beat TLO, the Team Went to a Barゲスト Oriol Vinyals · ホスト Lex FridmanOriol Vinyals on how DeepMind turned StarCraft II into a sequence problem, built a league of agents, and still refuses to call the game solved.
1:08:37ENLex Fridman· 2019年4月18日ポッドキャスト · 2 人A Bar in Montreal, Then a Night of Code: Ian Goodfellow on Why GANs Workゲスト Ian Goodfellow · ホスト Lex FridmanLex Fridman talks with Ian Goodfellow about the 2014 invention of generative adversarial networks, adversarial examples as a security problem, and what still has to be built before machines can hold a fact the way a person does.
1:20:21ENLex Fridman· 2019年1月19日ポッドキャスト · 2 人Einstein Was the Worst of Five Ph.D. Studentsゲスト Tomaso Poggio · ホスト Lex FridmanMIT neuroscientist Tomaso Poggio on why intelligence is science's deepest problem, and what brains still have to teach machines.
46:25ENLex Fridman· 2019年1月17日ポッドキャストDeep Learning at the Edge of 2019: BERT, Autopilot, and the Ideas That Broke Throughホスト Lex FridmanA tour of the architectural, applied, and automation breakthroughs that defined deep learning in 2018 and set up 2019.
1:19:59ENLex Fridman· 2018年12月23日ポッドキャスト · 2 人Schmidhuber’s bet: true meta-learning rewrites the learner, not the last layerゲスト Juergen Schmidhuber · ホスト 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· 2018年12月16日ポッドキャスト · 2 人A one-legged robot learned a backflip from "this is better"ゲスト Pieter Abbeel · ホスト 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· 2018年11月16日ポッドキャスト · 2 人The Hardest Part of Learning Was Left Out of the Textbooksゲスト Vladimir Vapnik · ホスト 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· 2018年10月20日ポッドキャスト · 2 人An Adult Can Change Last Year's Mind. A Network Still Cannot.ゲスト Yoshua Bengio · ホスト 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· 2016年9月27日ポッドキャストFrom Word Vectors to Memory Networks: The Building Blocks of Deep NLPホスト 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ポッドキャストDeep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network Foundationsホスト 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ポッドキャストDeep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZeroホスト 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ポッドキャストIs Language or Vision Harder? Ilya Sutskever on the Unity of Machine Learningホスト 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 Fridmanポッドキャスト · 2 人Deep Learning Is a System 1 Machine: Daniel Kahneman on What AI Still Lacksゲスト Daniel Kahneman · ホスト 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.
1:25:16ENLex FridmanポッドキャストFrom Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional Networksホスト 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 Fridmanポッドキャスト · 2 人Vision or Lidar, Human or Machine: Lex Fridman's 2019 Map of the Self-Driving Raceゲスト Self-Driving Cars · ホスト 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 FridmanポッドキャストFrom Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016ホスト 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ポッドキャストCaging the Neural Network: How Aptiv Thinks About Safe Self-Drivingホスト 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ポッドキャストSteering Through Time: How Recurrent Networks and LSTMs Learn from Sequencesホスト 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ポッドキャストDeep Learning Plus One Idea: Ilya Sutskever on Building AGIホスト 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.
1:31:52ENLex FridmanポッドキャストFrom Phonemes to CTC: How Deep Learning Rebuilt Speech Recognitionホスト 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.もっと見る83 件中 24 件を表示