neural control

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 opening lecture of Steve Brunton's Control Bootcamp, covering the kinds of control and why closed-loop feedback matters. It starts a series that follows the control chapter of the Brunton and Kutz data-driven science book.

A clip from Jim Jefferies' Netflix special BARE in which he comedically dissects American gun culture and gun control arguments.

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.

Dave Jones of EEVblog looks at a sub-3-cent microcontroller from Padauk and other obscure Chinese manufacturers. He shows how to find such parts and where to buy them in stock.

A Daily Show segment in which John Oliver examines the argument that gun control does not work, using Australia's experience after the Senate rejected the Manchin-Toomey amendment. It is a comedic, man-on-the-street style piece.

John Oliver's Last Week Tonight segment covers the working conditions of US air traffic controllers and the understaffing, outdated equipment (including floppy disks) and funding structure of the FAA. It mixes comedy with policy criticism.

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.

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.

Ben Eater writes a program in a made-up machine language and walks through the control logic an 8-bit breadboard CPU needs to execute it. It is part of his build-an-8-bit-computer series.

Andreas Antonopoulos argues that money has a fourth function beyond store of value, medium of exchange and unit of account, which is as a system of control. He covers the history of money and why it does not flow freely.

Real air traffic control audio of the Air Astana flight whose flight controls had been wired in reverse by a maintenance error. The pilots struggle to keep control while ATC tries to help.

A 1953 US Navy training film explaining the basic mechanisms in mechanical fire control computers aboard ships. It shows how gears, differentials and cams solved mathematical problems in permanent mechanical form.

A 1953 US Navy training film on the basic mechanisms in fire control computers: shafts, gears, cams and differentials. It shows how these mechanical parts compute ship and target firing solutions.

A lecture from MIT's Missing Semester course covering version control with git. It builds up git from its data model rather than from commands.

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

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.

A special lecture from MIT's Private Pilot Ground School in which Lt. Col. Randy Gordon, a fighter and test pilot, describes F-22 flight controls. Topics include thrust vectoring, the pilot command system and how software handles failures.

Johns Hopkins APL shows Les Baugh, a bilateral shoulder-level amputee, controlling two Modular Prosthetic Limbs by thought after a short training period. Nerves rerouted to his chest drive the arms.

Part one of Sandia National Labs' first-person documentary on the use control, detonation safety and survivability of US nuclear weapons. It covers nuclear sharing in NATO and how control of use was separated from possession, leading to the always/never problem.

A short demo of an open-source Krita plugin that uses Stable Diffusion to generate and edit images in place. It adds ControlNet scribble and line-art support. You select an area, push a button, and new matching content appears.

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.

An American Airlines training video by Captain Warren VanderBurgh on control malfunctions and flight instrument anomalies. It discusses real incidents such as runaway trim and instrument failures and how crews should respond.

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.

Valve's short video on building the Steam Controller on a heavily automated assembly line, which the company designed itself. It shows the robotic manufacturing process and US final assembly.

Terry Davis, author of TempleOS, demonstrates his SimStructure physics simulator and builds a PID controller using math from Numerical Recipes in C. The description notes PID controllers are used in everything from rockets to espresso machines.

A TU Vienna demo of a double inverted pendulum on a cart, using constrained feedforward and optimal feedback control for swing-up and point-to-point motion.

Fully Charged gets an exclusive first drive of the Porsche Taycan, running 0-200 km/h launch control repeatedly. It covers the car's twin-motor 800-volt specs, claimed range and fast charging.

A TU Wien control-systems demo in which a triple pendulum on a cart is swung up and stabilized using constrained feedforward plus optimal feedback control. It accompanies a 2013 Automatica paper.

Ben Heck modifies a keyboard with magnets, Hall effect sensors and an Xbox controller so the WASD keys give analog control. He walks through the hardware build.

Dashcam footage of a Tesla Model S on adaptive cruise control hitting a stopped van, with the driver listing the safety systems that failed to react. The uploader still calls the Model S the best car in the world.

Linus Torvalds gives a Google tech talk on git, the source control system he created two years earlier. He argues for distributed version control over centralized systems such as CVS and Subversion.

SQLite author Richard Hipp's talk at SouthEast LinuxFest criticizing Git's workflow and introducing Fossil as an alternative. He lists Git enhancements and argues for keeping history intact.

A video presenting an Intel research paper on enhancing the photorealism of synthetic images. A convolutional network uses rendering intermediates, shown on GTA V footage that comes out looking like real street scenes.

Kevin Spacey, giving the MacTaggart Lecture at the Edinburgh Television Festival, urges TV channels to give viewers control. He points to Netflix's House of Cards release as evidence that audiences want to watch on their own terms.

A short research demo of Autonomous Intersection Management, a protocol in which self-driving cars reserve slots through an intersection instead of obeying signals or stop signs. It uses UT Austin's autonomous vehicle Marvin and a simulation to show cars crossing without stopping.

In a TEDGlobal talk, Raffaello D'Andrea demonstrates quadcopters that play catch, balance, learn and coordinate, using algorithms that treat them like athletes. It includes Kinect-controlled quads.

A short MIT Aerospace Controls Lab demo from 2011 of a variable pitch quadrotor flying.

Andrew Huberman's long Huberman Lab episode is a masterclass on dopamine. It covers the neural circuits, peaks and baselines, dopamine depletion, and 14 tools for motivation, focus and avoiding addiction.