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.

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.

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.

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.

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.

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.

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 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.

A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences. It shows how a neural network can produce usable renders from very few samples.

Veritasium examines which experts have real expertise, drawing on chess research and work by Klein and Kahneman. It explains that expertise comes from pattern recognition built through deliberate practice in valid, feedback-rich environments.

Veritasium examines research suggesting science explainer videos like Khan Academy's make students feel they understand while tests show they have not learned, because misconceptions go unaddressed. It suggests how to partly fix this.

Kyle Hill explains what nuclear waste actually is and how it is stored, arguing that the problem was effectively solved decades ago. It covers solid shielded waste and deep geological storage.

A short TED-Ed animated lesson by Anita Collins on what happens in the brain when people play a musical instrument. It argues that playing engages many brain areas at once, like a full-body workout, with long-term benefits.

A Veritasium explainer on how the brain works and how we learn. It is inspired by Kahneman's Thinking, Fast and Slow and covers System 1 and System 2 thinking and why harder learning builds skill.

Yuta asks whether native Japanese speakers can actually write kanji by hand, showing that many struggle to recall characters from memory.

CGP Grey argues for picking a theme for the year or season instead of setting goals or new year's resolutions. He explains how a theme gives direction without a pass/fail target.

CGP Grey argues that your brain treats a whole home as one room during lockdown, blurring work, rest and leisure. He recommends creating separate spaces and routines for different activities to stay balanced.

CGP Grey's sarcastic animated video adapted from the book How to Be Miserable, listing habits that reliably make people unhappy. By inverting the advice, it shows what to avoid and prompts reflection on goals and routines.

A short How to ADHD explainer, featuring Brendan Mahan, on why simple tasks can feel impossible for people with ADHD. It introduces the 'wall of awful', a pile of past failures, shame and anxiety that builds up in front of a task and blocks starting it.

Zack Freedman gives advice on why makers fail to finish projects, including scrapping bad ideas, showing work publicly and writing a plan that keeps projects fun. It is aimed at hardware DIY but generalizes.

An RSA Animate illustrating a lecture by psychologist Philip Zimbardo on how people's perspectives on time (past, present, future) shape work, health and well-being.

Harvard professor Arthur Brooks explains why boredom is useful rather than something to avoid. He describes how a wandering mind engages the brain's default mode network, which supports creativity and curiosity, and suggests it may protect against depression.

An animated 11-minute tour of the whole field of mathematics as a single map, showing how pure and applied math and their sub-fields relate to each other.

jan Misali traces the history of the letter W, including why it is called double u. The video is part of a series of deep dives into individual letters.

Curious Droid asks what traces human civilization would leave in the geological record 65 million years from now. It considers how thin the fossil record of humanity might be.

PBS Space Time argues that the speed of light is better understood as the speed of causality, the universal limit on how fast cause and effect propagate. Light travels at that speed because it is massless, but the limit itself is a property of spacetime.

Kaze Emanuar explains how he rewrote and optimized the Super Mario 64 source code so it runs far faster on real N64 hardware. He covers performance bottlenecks and fixes in detail for his ROM hacks.

An Every Frame a Painting video essay on how Akira Kurosawa used movement, weather and composition to tell stories. It draws on clips and interviews with other filmmakers.

PBS Space Time explains Noether's theorem: conservation laws such as energy and momentum are consequences of deeper symmetries. It also covers why those laws hold only under certain conditions.

Climate Town gives a comedic, fast-paced account of how the plastics industry promoted recycling, including the resin-code recycling symbol, while knowing most plastic could not be economically recycled. It points viewers to the Frontline documentary Plastic Wars for a deeper treatment.

A PBS Space Time episode asking what matter, mass, and energy really are, starting with inertial versus gravitational mass and what mass-energy equivalence means.

A PBS Space Time episode on how the Higgs mechanism gives particles mass, prompted by Fermilab's heavier-than-expected W boson measurement. It goes beyond the usual pop-science treatment without heavy math.

A PBS Space Time episode asking what black holes really are and whether events can happen inside them. It covers event horizons, time dilation and common misconceptions about black holes.

The first video in a series on extremely large numbers, introducing the topic with examples. Later parts go deep into the fast-growing hierarchy.

A video arguing that exercise matters for the brain as much as the body, linking movement, the nervous system and BDNF to learning and memory. It draws on research connecting complex movement to brain development.