learning by doing

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 David Silver's reinforcement learning course, introducing the field and its basic concepts. The course follows the Sutton and Barto textbook.

Martin Gorner's Devoxx talk introduces deep learning with TensorFlow, walking through neural networks for MNIST, how to choose an architecture and how to diagnose networks that fail to train.

Machine Learning Street Talk interviews Paul Lessard about Categorical Deep Learning, which uses category theory and monads to make neural network architectures more interpretable and composable. They also discuss neural networks' limits in reasoning and unbounded computation.

Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.

Valve's John McDonald presents at GDC 2018 on how Valve uses deep learning (VACnet) to detect cheaters in Counter-Strike: Global Offensive. He covers training on human-reviewed replays and how model output is confirmed by manual review.

A GDC 2018 talk by Valve's John McDonald on VACNet, a deep learning system that analyzes CS:GO gameplay to detect cheaters. It covers how the model is trained on human-reviewed Overwatch cases and how its output feeds human moderation.

Jonathan Blow gives a roughly 90-minute talk, followed by Q&A, on how video games could actually improve education, in contrast to what is currently being tried.

The first lecture of Andrew Ng's Stanford CS229 Machine Learning course, giving an overview of the course. It introduces supervised and unsupervised learning, learning theory and reinforcement learning.

The first lecture of Caltech's CS 156 Machine Learning course by Yaser Abu-Mostafa, introducing the learning problem and supervised, unsupervised and reinforcement learning. It is one of 18 lectures in the Learning from Data course.

The first episode of Google's Machine Learning Recipes series. It introduces machine learning and builds a first supervised-learning classifier in about six lines of Python using scikit-learn.

3Blue1Brown's visual walkthrough of the attention mechanism inside transformers, covering self-attention, multiple heads and cross-attention. It is chapter 6 of his deep learning series.

Memories is a 256-byte MS-DOS demo that packs eight effects and MIDI soundscapes into a tiny program. It won first place at Revision 2020.

Max Tegmark's MIT CBMM talk on why deep learning works so well. He argues that the laws of physics and the symmetries in physical data make it compressible into small neural networks, tying physics to network structure.

A Ukrainian documentary about the liquidators who cleaned radioactive debris off the Chernobyl reactor roof in two-minute shifts. It presents their firsthand accounts and footage of the work.

Mark Rober and Jabril build an app that uses machine learning to decode baseball sign sequences. The video also explains neural networks in a simple, accessible way.

MIT 22.01 lecture by Michael Short explaining the Chernobyl accident technically, including RBMK reactor positive feedback, xenon poisoning and the cascade of human errors during the test.

Channel 4 News reports on undercover Greenpeace footage of an ExxonMobil lobbyist describing efforts to weaken climate legislation. Exxon disputes the claims.

Engineering Explained compares Lexus's steer-by-wire yoke on the RZ 450e with Tesla's yoke. It covers how steer-by-wire works and how variable steering ratios address the yoke's flaws.

The first part of an Al Jazeera undercover investigation into the Israel lobby in Britain, covering efforts to influence youth groups and the National Union of Students, including a smear campaign against its president.

Dwarkesh Patel interviews Andy Matuschak on how he learns, why memorization matters for understanding, and why most learning tools fail. The conversation also covers handling confusion and the role of tutoring.

Viznut's third bytebeat video presents music generated by very short C programs and JavaScript expressions. It links to online tools and deeper analysis of one-line music.

A CNN report in which Nima Elbagir witnesses migrants being auctioned as slaves at a property outside Tripoli, Libya.

A YouTuber explores the Chernobyl zone in 2013, takes a gamma spectrum of a hot reactor fuel fragment, and jokes about a radioactive ant bite. It is a hands-on amateur look at radiation in the exclusion zone.

A short clip from a Canal+ interview in which a Monsanto-linked lobbyist says Roundup is safe to drink, then declines when offered a glass. The clip circulated widely as an example of industry spokespeople not trusting their own claims.

Ali Rahimi accepts the NIPS 2017 Test of Time Award and argues that machine learning has become alchemy, with practice running ahead of understanding.

Viznut demonstrates bytebeat, experimental music generated by extremely short C programs. It is the first of a series of videos on the technique.

Musician and audio engineer Benn Jordan tries Dolby Atmos as a consumer, covering the theory of immersive audio, its business model, and home theater and headphone listening. He concludes it often falls short of the pitch.

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.

Lesson 1 of fast.ai's Practical Deep Learning for Coders, taught by Jeremy Howard. It takes coders from running code in a Jupyter notebook straight into training a real image model.

Drummer Larnell Lewis hears Metallica's Enter Sandman for the first time on Drumeo and learns to play it by ear, using his musical vocabulary.

Linus Tech Tips explains how Windows Modern Standby causes laptops to drain battery while asleep, arguing it makes Windows laptops hard to recommend compared to MacBooks.

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.

Louis Rossmann reacts to lobbyist ads in the Massachusetts right-to-repair ballot fight that suggest repair access would enable domestic abuse and discrimination, and urges support for the campaign.

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.

The Pinkfong Baby Shark Dance children's song video, one of the most viewed videos on YouTube.

Jim Weirich's RubyConf 2012 talk derives the Y combinator step by step, live-coding in Ruby lambdas. It builds up an understanding of functional programming and lambda calculus from first principles.

3Blue1Brown's first chapter on deep learning explains what neurons and layers are and the math underlying a basic neural network, using handwritten digit recognition with visual animations.

Ruby developer Avdi Grimm gives a seven-minute tour of Pharo Smalltalk's development environment, focusing on tools like search-by-example and the integrated, live coding experience.

Veritasium's Derek Muller gives a Perimeter Institute livestream on how AI might change teaching and learning. He draws on past technology shifts and cognitive science to argue that learning requires effortful repetition.