deep learning

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.

3Blue1Brown's second neural network chapter explains cost functions and gradient descent, showing how a network learns by minimizing error during training.

3Blue1Brown's visual explanation of how transformers and GPT-style language models work, tracing data through tokens, embeddings and attention.

Yosh trains a reinforcement learning agent to drive Trackmania until he can no longer beat it. The video explains how the training works and the design choices involved.

A Veritasium video on AlphaFold, DeepMind's protein structure prediction system, and the protein design work it enabled. It features interviews with John Jumper and with David Baker's protein design group and explains why predicting protein folding matters.

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.

A Welch Labs explainer on neural scaling laws and the compute-efficient frontier, asking why model loss seems to hit a line it cannot cross. It draws an analogy to an ideal gas law for AI.

Veritasium explains why analog computing may suit AI workloads, covering old analog computers, The Analog Thing and Mythic's analog chips that use flash memory for neural network inference. It argues digital hardware is hitting limits.

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.

Roaring Kitty's July 2020 analysis of GameStop, arguing a bullish deep-value case when the stock was about $4 and short interest exceeded 100%. It covers fundamentals, cash balance and technicals.

Soup Emporium's deep dive argues that Yellowstone is not a ticking timebomb. It goes through uplift and subsidence, earthquakes and what the caldera really is, to rebut supervolcano doom claims.

Tom 7 (suckerpinch) delivers a long, comedic digression on gradient descent and floating-point imprecision. He shows how rounding behavior can supply the nonlinearity needed to build a neural network.

A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.

Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.

Gamers Nexus benchmarks the Ryzen 9 7950X in its BIOS Eco Mode presets (65W, 105W and stock 170W). It measures the performance cost against the power and heat savings.

A long video essay on the claim that chemicals such as atrazine are feminizing frogs. It covers the science, the EPA and the role of chemical companies.

Pannenkoek2012's commentated tool-assisted Super Mario 64 run collecting the Watch for Rolling Rocks star with half an A press, using parallel universes and QPU movement. The video is marked outdated in favor of a newer version.

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.

Technology Connections takes a long, detailed look at how a 1970s electromechanical pinball machine works, from relays to stepper motors and mechanical logic. It is the first part of a series.

Technology Connections' long closing video in his heat pump series, arguing that adopting heat pumps is well within reach. It explains how they work and what it takes to start using them.

A 36-minute animated deep dive from Branch Education into how DRAM works. It shows how memory connects to the CPU and how billions of bits are stored in nanoscale capacitor cells. It also covers why DRAM sits between SSDs and the processor.

Retro Game Mechanics Explained dissects how Atari's Quadrascan vector displays and vector generator hardware drew games like Asteroids and Tempest.

Branch Education's animated deep dive into ASML's EUV photolithography machine and how it prints nanometer-scale transistors onto chips. It covers the system's components and the process of chip manufacturing.

WIRED has UCLA professor Amit Sahai explain zero-knowledge proofs to a child, a teen, a college student, a grad student and an expert. Each round goes deeper into the cryptography and why it matters.

Veritasium explains how ASML's EUV lithography machines make the most advanced computer chips, covering the engineering of the light source, mirrors and the supply chain around them. It is a long-form explainer on the world's most complex commercial machine.

Noodle explores how retro pixel art was designed for CRT displays and why games look different on LCDs, with input from pixel artists and CRT researchers.

A Veritasium video that follows the principle of least action from Bernoulli and Newton to quantum mechanics, asking whether light takes all possible paths at once. It includes experiments showing quantum waves.

Scott Manley examines why SpaceX, Google and others are looking at orbital data centers. He walks through the economics, heat rejection and solar power arguments, with links to the Lumen/Starcloud and Google Suncatcher papers.

3Blue1Brown introduces group theory and abstract groups, then builds toward classification of finite simple groups and the enormous Monster group with its 196,883 dimensions.

The Signal Path takes apart a Starlink dish layer by layer, analyzing the phased array RF design, system architecture and integrated circuits, with an X-ray of the RF stack.

GoldenSound publishes music on Tidal to test MQA, a deep dive into the format's claims and problems including its leaky filter. Testing begins around the 5:45 mark.

Rick Beato analyzes a pop song he argues is among the most harmonically complex ever, breaking down its chords and key changes. It is a music theory deep dive aimed at general music fans.