deep learning

The first lecture of Stanford's Natural Language Processing with Deep Learning course, taught by Chris Manning and Richard Socher. It introduces NLP and word vectors, including SVD, skip-gram, CBOW, negative sampling and word2vec.

Bill Dally of NVIDIA gives a University of Washington lecture on trends in deep learning hardware. It covers numeric formats, specialized instructions, energy per operation and co-design of hardware and software.

Sacha Arnoud, Waymo's Director of Engineering, gives a lecture in MIT's 2018 deep learning for self-driving cars course on the rise of machine learning in autonomous vehicles. It covers how Waymo uses deep learning and how it handles tricky driving situations.

The introductory lecture of Richard Hamming's capstone course, The Art of Doing Science and Engineering: Learning to Learn. It focuses on style of thinking and on educating rather than training, using technical material only as illustration.

The first lecture of Stanford's CS231n course on convolutional neural networks for visual recognition. It surveys the history and key challenges of computer vision, from the Cambrian explosion and Hubel and Wiesel to ImageNet.

The final lecture of Richard Hamming's Learning to Learn course, from 1995, based on his well-known talk 'You and Your Research'. It covers how to do important work and build a career.

Andrej Karpathy's three-hour-plus general-audience deep dive into how ChatGPT-style LLMs are built, covering the full training stack from pretraining to post-training. It also gives mental models for their quirks, like hallucination, and how to use them well.

A university lecture from CS480/680 by Pascal Poupart on attention mechanisms and transformer networks, worked through on a chalkboard.

Geoffrey Hinton gives an MIT talk on what is wrong with convolutional neural networks and introduces his capsules project. The description points to the capsule network papers.

Leo Dirac explains how transformer models have replaced LSTMs in NLP. He gives background from bag of words through RNNs and LSTMs, then a technical deep dive into multi-headed self-attention and positional encoding, with sample code.

The first lecture of David MacKay's Cambridge course on information theory, pattern recognition and neural networks. It introduces the core ideas of his book Information Theory, Inference, and Learning Algorithms.

Peter Norvig's UBC distinguished lecture on how massive amounts of simple data, such as for language modeling, can yield understanding that hand-built models could not.

Andrej Karpathy builds the GPT tokenizer from scratch, implementing byte pair encoding along with encode and decode. He shows how many odd LLM behaviors trace back to tokenization, and covers Unicode byte encodings along the way.

John Gustafson presents posits, a proposed drop-in replacement for IEEE 754 floats that is simpler in hardware and more flexible in precision. The seminar includes a live demo and machine learning results.

Richard Hamming's 1995 recording of his talk 'You and Your Research', drawn from his graduate engineering course. He discusses how great scientists pick important problems and build careers, drawing on his years at Bell Labs.

Andrej Karpathy's first Neural Networks: Zero to Hero lecture, which builds micrograd, a tiny autograd engine, from scratch in Python. It explains backpropagation and neural network training step by step, assuming only basic Python and some high-school calculus.

Geoffrey Hinton's 2025 Royal Institution Discourse on what AI has learned from biological intelligence and how it might surpass it. He explains neural networks and argues that human language use resembles what backpropagation-trained networks do.

Sasha Rush surveys linear RNNs and state space models as replacements for attention in transformer-style models, in a talk for MLSys. It covers the foundational preliminaries and predates Mamba.

A 15-minute clip of linguist Stephen Krashen discussing language acquisition, drawn from the 1980s. It presents his input hypothesis and the distinction between acquisition and learning.

The first lecture of Gilbert Strang's MIT 18.06 Linear Algebra course, covering the geometry of linear equations. It opens a full 35-lecture university course.

A lecture from the 1980s by linguist Stephen Krashen on how people acquire language. He explains his comprehensible input hypothesis for second-language acquisition.

Patrick Winston's long-running MIT lecture on public speaking teaches heuristic rules for talks. It covers how to start, use time and place, boards, props and slides, and how to inform, persuade and finish.

Randy Pausch's 2007 last lecture at Carnegie Mellon, given as he was dying of pancreatic cancer. He reflects on achieving childhood dreams, overcoming obstacles and helping others reach theirs.

Psychology professor Marty Lobdell gives a one-hour lecture on how to study effectively, covering short focused sessions with breaks, study environment, note-taking and memory techniques. It was aimed at students who cram without improving.

A roughly three-hour San Francisco workshop by Marshall Rosenberg on Nonviolent Communication, with full English subtitles added by a fan. He teaches the model with his jackal and giraffe language examples.

Larry McEnerney of the University of Chicago Writing Program argues that good writing is defined by what readers value, not by rules or the writer's own ideas. He explains why academic habits fail outside academia and how to write so readers find the work valuable.

Carnegie Mellon professor Randy Pausch gives a lecture on time management at the University of Virginia in 2007. He covers practical habits such as tackling important tasks first and distinguishing important from urgent work.

Randy Pausch, a Carnegie Mellon computer scientist and virtual reality pioneer who was dying of cancer, gives his 'Last Lecture' about achieving childhood dreams and living well. The recording is a full-length talk of about 104 minutes.

Harvard physicist Eric Mazur explains how he realized his students were memorizing rather than understanding, and how he changed his teaching. He presents peer instruction and data showing improved student performance.

A clip of Richard Feynman contrasting the Greek and Babylonian traditions of mathematical reasoning. It compares the axiomatic approach of mathematicians with how physicists use mathematics.

Russell Barkley gives the keynote at UNC's 2012 Burnett Seminar on ADHD. He presents it as an executive function disorder and discusses its effects and how to help.

The first lecture of MIT's 6.001 (SICP) with Abelson and Sussman, giving an overview of the course and an introduction to Lisp. It argues that computer science is about managing complexity and abstraction, not computers.

The first lecture of Jordan Peterson's 2017 Maps of Meaning course, setting out the Cold War context for his theory of belief and culture. He introduces the narrative structure of culture and archetypal characters for the individual, the known and the unknown.

The opening lecture of MIT 6.824 Distributed Systems (Spring 2020), introducing the course and core challenges of distributed systems. It begins a playlist that goes on to cover Raft and other consensus papers in Go.

Leonard Bernstein's 1973 Norton Lectures at Harvard, starting with Musical Phonology. He draws analogies between music and linguistics, including references to Chomsky.

Chris Shore of the Centre for Computing History explains how Colossus was built, how it worked, and how it affected the course of World War II. It is an hour-long museum lecture on the codebreaking computer.

Lecture 1 of Harvard's Statistics 110 with Joe Blitzstein, introducing sample spaces, the naive definition of probability, counting, binomial coefficients and the sampling table.

An eight-minute excerpt of a 1983 video featuring Seymour Papert, creator of Logo, on children learning programming and abstract ideas through embodied play. It shows kids acting out the Logo turtle.

Richard Hamming's 1995 lecture on n-dimensional space, showing how geometric intuition about spheres and cubes breaks down in high dimensions. It is part of his course on learning to learn.

The introductory lecture of Stephen Boyd's Stanford Convex Optimization I course (EE 364A). It outlines convex sets, functions and problems, and the course's coverage of least-squares, linear and semidefinite programming, duality and interior-point methods.