liquid networks

Andrej Karpathy's first Neural Networks: Zero to Hero lecture, which builds micrograd, a tiny autograd engine, from scratch in Python. It explains backpropagation and neural network training step by step, assuming only basic Python and some high-school calculus.

The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

Steven Johnson's TED talk argues that good ideas come from connected, slow-building hunches and liquid networks, from London coffee houses to Darwin to the modern web, rather than lone Eureka moments.

A five-minute animated explainer of liquid democracy, in which voters can delegate their vote to trusted people. It starts from the origins of democracy and contrasts direct and representative models.

Geoffrey Hinton's 2025 Royal Institution Discourse on what AI has learned from biological intelligence and how it might surpass it. He explains neural networks and argues that human language use resembles what backpropagation-trained networks do.

MIT's Donald Sadoway presents the liquid metal battery as a design for grid-scale stationary electricity storage, at an Imperial College London event in 2018. He covers the grid benefits of massive-scale storage.

Tech Ingredients explains the principles of magnetohydrodynamics and builds several demonstrations, including propelling liquid metal and electrolytes with magnets and a railgun-style setup.

Mark Rober builds a hot tub filled with sand fluidized by air blown from below, so that the sand behaves like a liquid. He explains how fluidized beds work and shows people swimming in them.

Geoffrey Hinton gives an MIT talk on what is wrong with convolutional neural networks and introduces his capsules project. The description points to the capsule network papers.

The first lecture of Stanford's CS231n course on convolutional neural networks for visual recognition. It surveys the history and key challenges of computer vision, from the Cambrian explosion and Hubel and Wiesel to ImageNet.

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

A short demo video for NVIDIA's StyleGAN paper, which proposes a style-based generator for GANs. It shows face synthesis with style mixing and scale-specific control over attributes like pose and freckles.

Kirk Sorensen's Google Tech Talk on liquid-fluoride thorium reactors, a design that could burn nuclear waste and use thorium as fuel. It draws on Oak Ridge National Laboratory work from the 1950s and 60s.

A university lecture from CS480/680 by Pascal Poupart on attention mechanisms and transformer networks, worked through on a chalkboard.

Disney Research presents Touche, a swept frequency capacitive sensing technique that recognizes complex hand and body configurations, and adds touch sensitivity to humans, liquids and everyday objects.

A 2008 Google Tech Talk making the case for the liquid fluoride thorium reactor as an abundant, safe source of electrical power. It covers the technical motivations and design of thorium molten-salt reactors.

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.

LockPickingLawyer shows what happens when liquid gallium is applied to an aluminum Abus padlock, which weakens and breaks the metal. It is a short demonstration of gallium's effect on aluminum.

The shareholder speech by Larry the Liquidator, played by Danny DeVito, from the film Other People's Money. He argues that a dying company should be liquidated rather than kept alive.

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.

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.

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.

Alex Russell's Chrome Dev Summit 2016 talk on building web experiences that work on slow, flaky networks and low-power devices. It argues developers should focus on the performance of real-world mobile hardware rather than desktop machines.

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.

BobbyBroccoli documentary on the rise of Nortel Networks, once the dominant Canadian telecom giant, during the dot-com era. It is part one of a two-part story.

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.

Andrej Karpathy, then Tesla's head of AI, gives a CVPR 2021 workshop keynote on how Autopilot's neural networks work. A large part covers the move to a vision-only stack, including why radar was dropped and how vision produces depth estimates.

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.

Geoff Hinton's 2010 Google Tech Talk on deep belief networks, learning layers of representation one at a time from unlabeled data, and extending them with multiplicative interactions.

Footage shot in New York City in 1911 by a Swedish film company, upscaled to 4K and 60 fps with neural networks and optionally colorized. The creator notes the colors are artificial and added only for ambiance.

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.

The first lecture of Stanford's CS231n Winter 2016 course on convolutional neural networks for visual recognition, introducing the course and the historical context of computer vision.

MIT professor Donald Sadoway argues that grid-scale storage is the missing piece for renewable energy. He sketches at the blackboard how large, cheap liquid-metal batteries could store wind and solar power.

WSJ's Joanna Stern interviews Apple's Craig Federighi and Greg Joswiak at WWDC 2025 about Siri's delays, AI strategy, the Liquid Glass redesign in iOS 26, iPad versus Mac, and tariffs.

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.

Engineering Explained examines BMW's Hydrogen 7, a V12 that burns liquid hydrogen or gasoline. He covers cryogenic storage at -253C and why the approach is impractical.

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.

Urs Hoelzle, Google's SVP of infrastructure, gives the 2012 Open Networking Summit keynote on how Google adopted OpenFlow and software-defined networking in its own networks. The slides are linked in the description.

Cloth Map documents Havana's SNET, a community-built private network that Cubans created because internet prices were high. It is used for gaming and sharing.