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 second neural network chapter explains cost functions and gradient descent, showing how a network learns by minimizing error during training.

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.

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 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.

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.

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.

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.

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.

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.

Yannic Kilcher walks through the Attention Is All You Need paper, which introduced the Transformer, a sequence model based solely on attention without recurrence or convolutions. He reviews the architecture and the paper's translation results.

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

Rob Miles explains on Computerphile how language models generate plausible text and how transformers improved on recurrent networks, with a look at what comes next.

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.

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.

CGP Grey explains the mess of Daylight Saving Time, including its dubious energy savings and the odd cases like Arizona that opt out. It is a short, simple explainer.

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.

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.

CGP Grey explains why "Indian" is often preferred over "Native American" in the United States, especially near reservations, and how many tribes exist in the US. He draws on conversations with people who identify as Indian.

Vsauce's explainer on Zipf's law, the pattern in which the frequency of a word is inversely related to its rank. It shows the pattern across many domains and discusses why it remains unexplained.

Vox explains the Berlin and Kay research showing that languages around the world tend to invent color words in the same order. It walks through the hierarchy and the debate around it.

Tom Scott-style exploration by suckerpinch (Tom7) of generalized anagrams where letters can be broken into pieces, called anagraphs, with a whimsical computational approach.

Vox breaks down how great rappers build rhymes, from Kurtis Blow's simple bars to Biggie's smooth flow and Kendrick Lamar's dense, fast delivery. It uses on-screen visualizations of rhyme structure.

Tom Scott argues that grammatical gender is a silly concept and that the singular 'they' is an established gender-neutral pronoun. The description carries later corrections and reflections he added in 2019.

David and Ben Crystal introduce the Original Pronunciation production of Shakespeare and show what it reveals about the history of English, including puns and rhymes lost in modern speech.

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.

Tom Scott explains phatic expressions such as hello, thank you and how are you, which carry social meaning rather than information, and why replies like no problem can seem rude to some people.

A re-upload of a video breaking down Eminem's rhyme schemes, showing multi-syllable and internal rhymes in songs such as Lose Yourself. It aims to show why he is considered a standout lyricist.

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.

Yuta, a Japanese YouTuber, explains whether Japanese speakers can read Chinese text. He shows how shared kanji let people guess meanings while the two languages remain completely different.

Numberphile explains the long and short scales for naming large numbers, covering millions, billions, trillions, milliards and the Greek myriad, with James Grime and Tony Padilla.

Dialect coach Erik Singer analyzes how accurate the accents are of 32 well-known actors, including Brad Pitt and Will Smith, in WIRED's breakdown.

Tom Scott makes a short descriptivist argument that language keeps changing and that casual internet writing conventions, like lowercase typing and dropped full stops, are legitimate. It is part of his Language Files series, written with Gretchen McCulloch.

A Langfocus video examining why Portuguese, especially European Portuguese, sounds like Russian or Polish. It compares shared sounds such as vowel reduction and palatalization.

A short animation from the DNA Learning Center showing how mRNA carries a gene's message to the ribosome, where tRNA and codons are used to assemble amino acids into a protein.

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.

3Blue1Brown visualizes high-dimensional spheres to explain a surprising puzzle about how a sphere fits in a box as dimensions grow. It builds geometric intuition for counterintuitive properties of high-dimensional space.

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.