deep learning

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.

3Blue1Brown's third deep learning chapter gives a visual, intuitive account of backpropagation and what happens to a neural network as it learns. A follow-up video covers the underlying calculus.

3Blue1Brown's chapter 4 on deep learning gives a more formal, symbol-based account of backpropagation calculus, connecting the intuition from the previous chapter to the math found in textbooks and code.

A short smartphone-recorded clip from a 2014 event in Paris where DeepMind CEO Demis Hassabis presents an AI learning to play old Atari games. The system learns from only the video signal and the score. Audio quality is poor.

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.

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.

A six-minute journey through the layers of a neural network using Deep Dream, with each frame fed back into the network starting from random noise and the targeted layer changing every four seconds. It is set to downtempo music.

3kliksphilip summarizes Valve's GDC talk on VACNet, a deep-learning system that flags CS:GO cheaters and feeds the Overwatch review queue. It covers Trust Factor, VAC, and how the data is collected and analyzed.

SethBling shows MarI/O, a program using neural networks and the NEAT genetic algorithm to learn to play Super Mario World. The description links the source code, the paper and background reading.

Full episode of Sassy Justice, a satirical local-news show from the South Park creators starring a deepfaked consumer advocate, Fred Sassy. It uses face-swapped public figures to comment on the dangers of manipulated video.

Matt Parker of Stand-up Maths demonstrates MENACE, Donald Michie's 1961 machine made of matchboxes that learns to play noughts and crosses through reinforcement. He builds and trains a physical version.

A Mandelbrot set zoom animation reaching a magnification of about 2.1x10^275, claimed as the deepest at the time (January 2010). Each frame was rendered separately over six months on 12 CPU cores.

Two Minute Papers covers a paper on speeding up fluid and smoke simulation with convolutional networks. It contrasts the approach with earlier regression forest methods.

A short video built around an animation of the roughly 10,000 galaxies in the Hubble Ultra Deep Field, placed at their measured redshift distances. It gives a brief history of deep field images and ends with a 3D fly-through.

Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.

Two Minute Papers covers OpenAI's multi-agent hide-and-seek experiment, in which agents learned emergent tool use and found ways to break the game's rules. It summarizes the 'Emergent Tool Use from Multi-Agent Interaction' paper.

A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks. The technology was later developed commercially.

Demis Hassabis of DeepMind speaks at Google Zeitgeist, saying human-level AI is decades away but the debate should start now. He covers DeepMind's focus on game-playing agents.

agadmator walks through a game in which DeepMind's AlphaZero beat Stockfish, ending in a famous zugzwang that leaves the engine helpless. He gives commentary on the moves.

Microsoft Research's Rick Rashid demonstrates a speech recognition and translation system, built on deep neural networks, that turns his spoken English into Chinese speech in 2012.

The video argues that machine-learning-based aimbots, which read the screen and drive the controls externally, could make cheating in FPS games undetectable. It explains how conventional aimbots work, how the new approach differs, and speculates on possible detection.

Tom7 explains and demos software that learns to play NES games by finding score patterns in memory and then searching for inputs that raise it. It is the video companion to his SIGBOVIK paper.

Veritasium debunks the idea of learning styles, such as being a visual learner, with an interview with Daniel Willingham and a memory experiment. It argues that a multimodal approach helps everyone.

Chris Lonsdale presents a TEDx talk on how adults can learn a language in about six months, centering on immersion, comprehensible input and a practical learning methodology.

Andrew, diagnosed with early onset Parkinson's at 35, shows how deep brain stimulation surgery has controlled his motor symptoms. The short video shows his tremors with the stimulator off and on.

A roughly 10-minute guided Non-Sleep Deep Rest session voiced by neuroscientist Andrew Huberman. It is meant to reduce daytime fatigue, improve focus and aid sleep.

Tom Scott, who never learned to ride a bike, gets lessons from Mike Boyd, a YouTuber known for learning skills quickly. The video follows an adult's attempt to learn cycling in a short time.

Andrej Karpathy's Databricks talk on Software 2.0, the shift from human-written code to code produced by neural network training. It covers how developer work moves toward curating datasets, the advantages and challenges, and opportunities for new tooling.

Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the wrong goal in training and misbehaves when deployed.

A 1970 demonstration of W. Timothy Gallwey, author of The Inner Game of Tennis, teaching a complete beginner to play tennis in about ten minutes. He chats with her, feeds balls and gives positive feedback instead of instruction.

A five-minute SuperMemo demo of incremental reading: importing a Wikipedia article on nutrition, extracting passages, making cloze deletions and finishing the item. It lists the keyboard shortcuts used.

Destin of Smarter Every Day learns to ride a bicycle whose steering is reversed, taking about eight months, and compares it with how his young son learned much faster. It illustrates knowledge versus understanding and brain plasticity in adults versus children.

Sal Khan of Khan Academy argues that schools push students forward with gaps in their foundations, and that students should instead master concepts at their own pace. He compares it to building a house on an unfinished foundation.

Part two of EEVblog's visit to the NASA/CSIRO Canberra Deep Space Communication Complex, showing the control room and how operators contact Voyager 2. It includes live data and spectrum displays.

Smarter Every Day host Destin Sandlin tries to hover a helicopter and finds it very hard. The video shows how the constant coordinated corrections across several control axes feel at first and how learning makes them automatic.

Josh Kaufman's TEDx talk argues that you can reach practical competence in almost any skill with about 20 hours of focused practice, rather than the 10,000 hours often quoted. He describes how becoming a parent led him to rethink how adults learn, and lays out a short method for rapid skill acquisition.

Eduardo Briceno gives a TEDx talk on mindset, contrasting fixed and growth views of ability. He argues that believing abilities can be developed encourages challenge, deliberate practice and grit.

Sentdex demonstrates GAN Theft Auto, a GameGAN-based neural network that recreates GTA V so the network itself is the playable environment. He shows the results and releases the code.

A short vintage film clip of Seymour Papert, creator of Logo, on using computers to spark children's imagination and learning.

A short cartoon explaining how language models like ChatGPT work, from autocomplete and conditional probabilities to neural networks, gradient descent and backpropagation. It shows how networks act as universal function approximators.