AI & Machine Learning

Deep learning, language models, reinforcement learning, statistical learning theory, representation learning, and vision.

8 courses · 111 standalone talks · 283 total lectures

All AI & ML Language Models & NLP (114)Deep Learning (87)Statistical Learning & Causality (60)Algorithms & Data Structures (43)Reinforcement Learning (38)Complex Systems & Scaling (21)Neuroscience & Cognition (19)Probability & Information Theory (17)machine learning (15)Moral & Political Philosophy (14)

Essential AI & ML courses

All 8 AI & ML courses →

Complete university lecture courses in ai & machine learning.

Caltech · CS 15618 lectures · 24h

AI & ML·undergraduate

Learning From Data

Prof. Yaser Abu-Mostafa·Caltech

Yaser Abu-Mostafa's famed Caltech course on statistical learning theory: Hoeffding's inequality, VC dimension, bias-variance tradeoff, regularization, support vector machines, and neural nets.

Start lecture 1

Syllabus →

Independent / Eureka Labs · NN-Z2H11 lectures · 20h

AI & ML·undergraduate

Neural Networks: Zero to Hero

Andrej Karpathy·Independent / Eureka Labs

From scalar autograd and backpropagation in pure Python up to modern Transformer language models built line-by-line from scratch.

Start lecture 1

Syllabus →

Stanford CS231n: Convolutional Neural Networks for Visual Recognition

Stanford University · CS231n16 lectures · 20h

AI & ML·graduate

Convolutional Neural Networks for Visual Recognition

Prof. Fei-Fei Li, Justin Johnson & Serena Yeung·Stanford University

Linear classifiers, computational graphs, backpropagation, convolutional architectures, batch normalization, training dynamics, object detection, semantic segmentation, and generative visual models.

Start lecture 1

Syllabus →

UCL / Google DeepMind · COMP008910 lectures · 16h

AI & ML·graduate

Introduction to Reinforcement Learning

Prof. David Silver·UCL / Google DeepMind

Foundational reinforcement learning course taught by AlphaGo lead researcher David Silver: Markov Decision Processes, Bellman optimality, dynamic programming, Monte Carlo, TD learning, and function approximation.

Start lecture 1

Syllabus →

UC Berkeley CS 285: Deep Reinforcement Learning

UC Berkeley · CS 28511 lectures · 4h

AI & ML·graduate

Deep Reinforcement Learning

Prof. Sergey Levine·UC Berkeley

Imitation learning, policy gradients, actor-critic algorithms, value-function Q-learning, model-based RL, offline reinforcement learning, exploration, and inverse RL.

Start lecture 1

Syllabus →

Stanford University · CS259 lectures · 10h

AI & ML·graduate

Transformers United

Stanford Guest Researchers·Stanford University

Research seminar examining self-attention architectures across language modeling, multimodal reasoning, robotics, biology, and scaling laws with leading industry and academic pioneers.

Start lecture 1

Syllabus →

AI & ML Double Feature

Two complementary ai & ml talks paired around a central intellectual tension.

Double Feature2 talks · 134m total

Compression vs. World Models

Does general intelligence emerge directly from unsupervised next-token compression, or does reasoning require explicit world models that plan in latent space?

Part I · Unsupervised compression57:21

An Observation on Generalization and Unsupervised Compression

Ilya Sutskever·Simons Institute

Part II · Objective-driven world models1:16:53

Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan

Yann LeCun·Harvard University

Standalone AI & ML talks

111

All 111 talks →

Self-contained lectures, Nobel addresses, and research colloquia you can watch in one sitting.

Machine Learning (CS 229): Lecture 1 - Course Introduction

1:08:40

AI & ML·Standalone Lecture

Machine Learning (CS 229): Lecture 1 - Course Introduction

Andrew Ng·Stanford University

Stanford Professor Andrew Ng introduces the foundational course in Machine Learning (CS 229), outlining key topics from statistical pattern recognition to modern applications.

2024 Nobel Prize Lectures in Economic Sciences: Institutions, Technology, and Prosperity

1:46:53

AI & ML·Public Colloquium

2024 Nobel Prize Lectures in Economic Sciences: Institutions, Technology, and Prosperity

Daron Acemoglu, Simon Johnson, James A. Robinson·Nobel Prize Outreach

The 2024 Nobel Laureates present their research on the endogenous formation of institutions and their profound impact on long-term economic prosperity and societal development, with particular attention to technology and historical disease environments.

CS231n Winter 2016: Lecture 1 - Introduction to Convolutional Neural Networks

1:19:08

AI & ML·Standalone Lecture

CS231n Winter 2016: Lecture 1 - Introduction to Convolutional Neural Networks

Andrej Karpathy·Stanford University

Andrej Karpathy introduces Stanford's CS231n course, providing an overview of convolutional neural networks and their historical context in visual recognition.

1:10:49

AI & ML·Standalone Lecture

Lecture 18: Frontiers (CS224R)

Chelsea Finn·Stanford University

This lecture explores cutting-edge research frontiers in deep reinforcement learning, examining advanced problem formulations and methodological approaches. It also addresses crucial aspects of deployment and robust evaluation strategies for complex RL systems.

Learning Representations: A Challenge for Learning Theory, COLT 2013

54:33

Theory & Algos·Conference Talk

Learning Representations: A Challenge for Learning Theory, COLT 2013

Yann LeCun·New York University

Yann LeCun examines the fundamental challenges of learning theory in the context of representation learning, presented at the Conference on Learning Theory (COLT) in 2013.

On the Emergence of Representational Geometry from Natural Language Statistics

1:08:42

AI & ML·Research Seminar

On the Emergence of Representational Geometry from Natural Language Statistics

Yasaman Bahri·Harvard University

Yasaman Bahri of Google DeepMind discusses the spontaneous emergence of intricate geometric structures in large language models, reflecting the semantic and conceptual organization of natural language.