Resultados · YoutuBlog

Canales actualizados recientemente

Elige uno para ver solo ese canalVer todos los canales →

PragerUanteayer

Y Combinatoranteayer

SemiAnalysishace 3 días

a16zhace 3 días

GOTO Conferenceshace 3 días

Latent Spacehace 4 días

Dwarkesh Patelhace 4 días

Adrian Twaroghace 5 días

Resultados

51 artículos

Ordenar

TemaFundamentos de ML Voces1 voz

Lex 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.Modelos y entrenamientoDeep LearningFundamentos de ML+2

Lex 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.Modelos y entrenamientoRecommendation systemsSearch & retrieval+3

Lex 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.Modelos y entrenamientoDeep LearningMultimodal AI+2

Lex 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.Modelos y entrenamientoReinforcement LearningAI research+3

Lex FridmanPódcastWhy AI Will Never Be Perfect: Lex Fridman's Case for Keeping Humans in the LoopPresenta: Lex FridmanIn MIT 6.S093's opening lecture, Lex Fridman lays out five research areas of human-centered AI, from machine teaching to arguing machines that flag their own uncertainty.Modelos y entrenamientoHuman-AI CollaborationFundamentos de ML+3

Lex FridmanPódcastFrom Pixels to Steering Wheels: Convolutional Networks and End-to-End DrivingPresenta: 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.Modelos y entrenamientoAutonomous DrivingDeep Learning+3

Lex 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.Modelos y entrenamientoReinforcement LearningDeep Learning+2

Lex FridmanPódcastTaming the Long Tail: How Waymo Builds a Self-Driving FactoryPresenta: Lex FridmanWaymo principal scientist Drago Anguelov explains how machine learning infrastructure, hybrid design and smart simulated agents tackle the rare events of autonomous driving.Modelos y entrenamientoAutonomous DrivingRobotics+3

Lex 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.Modelos y entrenamientoReinforcement LearningFundamentos de ML+3

Lex FridmanPódcastVapnik's Case for Learning by Predicates, Not Just by More DataPresenta: 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.Modelos y entrenamientoFundamentos de MLAI research+2

Lex FridmanPódcastTheano in an Hour: Symbolic Graphs, Automatic Gradients and a Compiler That Rewrites Your MathPresenta: 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.Modelos y entrenamientoDeep LearningFundamentos de ML+3

Lex 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.Modelos y entrenamientoReinforcement LearningFundamentos de ML+3

Lex 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.Modelos y entrenamientoReinforcement LearningDeep Learning+3

Lex FridmanPódcastThe Second 90%: What It Really Takes to Put Deep Learning on a Driverless CarPresenta: Lex FridmanWaymo's Sacha Arnoud walks MIT students through Waymo's history, its perception stack, and the industrial-scale labeling, compute and testing behind it.Modelos y entrenamientoAutonomous DrivingRobotics+3

Lex FridmanPódcastInside Torch and Autograd: How Deep Learning Libraries Compute GradientsPresenta: Lex FridmanAlex Wiltschko of Twitter walks through Lua Torch, then explains automatic differentiation and what separates modern deep learning frameworks.Modelos y entrenamientoFundamentos de MLDeep Learning+1

Lenny's PodcastPódcastModels Are Grown, Not Built: What Anthropic's Interpretability Research Sees Inside ClaudePresenta: Lenny RachitskyAnthropic researcher Emmanuel Ameisen explains how studying a language model's intermediate computations reveals concepts, plans and surprising quirks, and why that matters for alignment.Modelos y entrenamientoModel InterpretabilityAI research+3

Lex FridmanPódcastFrom Bag of Words to Attention: Quoc Le Teaches Sequence-to-Sequence Learning Through Email RepliesPresenta: Lex FridmanA Deep Learning School talk that builds sequence-to-sequence models step by step around one running example, automatic email reply, and then surveys memory and operation-augmented networks.Modelos y entrenamientoDeep LearningFundamentos de ML+2

Lex FridmanPódcastBigger Models, Cleaner Splits and Human Baselines: Andrew Ng's Practical Recipe for Applied Deep LearningPresenta: Lex FridmanIn a 2016 Deep Learning School talk, Andrew Ng distills lessons from leading Baidu's AI team into a workflow for diagnosing models, handling data and building a career.Modelos y entrenamientoFundamentos de MLDeep Learning+3

Lex FridmanPódcastLearning TensorFlow Hands-On: From a Mystery Line to Handwritten DigitsPresenta: Lex FridmanGoogle Brain's Sherry Moore walks a Deep Learning School audience through how TensorFlow works and two core labs, linear regression and MNIST digit recognition.Modelos y entrenamientoInfraestructura y despliegueOpen-source ecosystems+3

Lex FridmanPódcastWhy Simple Theories Win: Marcus Hutter on Occam's Razor, Compression and Kolmogorov ComplexityPresenta: Lex FridmanDeepMind researcher Marcus Hutter explains Solomonoff induction, why compression equals understanding, and how a simple universe can still look rich.Modelos y entrenamientoFundamentos de MLAI research+3

Lex FridmanPódcastStatistics as Decision-Making: Michael I. Jordan on Bayesians, Frequentists and the Ideas Between ThemPresenta: Lex FridmanBerkeley's Michael I. Jordan explains where statistics came from, why it is really about decisions, and how empirical Bayes and false discovery rate bridge two rival philosophies.Modelos y entrenamientoFundamentos de MLDecision Making+2

Lex FridmanPódcastGlitches as Features: What John Hopfield Says Artificial Neural Networks Are MissingPresenta: Lex FridmanIn a short conversation with Lex Fridman, physicist and neural-network pioneer John Hopfield compares evolved brains with today's artificial networks and explains why he expects AI to borrow from biology generation after generation.Modelos y entrenamientoNeuroscience & AIFundamentos de ML+3

Cognitive Revolution "How AI Changes Everything"PódcastPause Tokens, Analogical Prompts and Ring Attention: A Tour of the Transformer's Next UpgradesPresenta: Nathan LabenzNathan Labenz and Trey Kollmer walk through five recent papers on pausing, backspacing, prompting, streaming and long-context training, and sketch how they might combine into a more capable model.Modelos y entrenamientoTransformers & attentionFundamentos de ML+3

Lex 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.Modelos y entrenamientoDeep LearningAutonomous Driving+3

Cargar másMostrando 24 de 51