machine learning

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.

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.

A short smartphone-recorded clip from a 2014 event in Paris where DeepMind CEO Demis Hassabis presents an AI learning to play old Atari games. The system learns from only the video signal and the score. Audio quality is poor.

A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.

OpenAI's short demo of agents playing hide-and-seek in a simulated environment. Through self-play, the agents develop six progressively more complex strategies and counter-strategies, including tool use.

Tom7 explains and demos software that learns to play NES games by finding score patterns in memory and then searching for inputs that raise it. It is the video companion to his SIGBOVIK paper.

Toyota Research Institute presents an approach for teaching robots new dexterous behaviors from human demonstration. It explains why this capability matters and what advances made it possible.

Symbolics developer Kalman Reti gives a short introductory demo of a Symbolics Lisp Machine running Genera in an emulator. It shows the context-aware command line, typed on-screen objects, and the live-editable system, including swapping in a C-compiled JPEG decoder.

A two-hour complete longplay of the 1993 MS-DOS puzzle game The Incredible Machine, in which players assemble Rube Goldberg contraptions to complete simple tasks.

A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks. The technology was later developed commercially.

A short Unitree promo for its G1 humanoid robot, priced from $16K, showing agile motion, dexterous hands and imitation and reinforcement learning.

A bot built by Robin Baumgarten plays Infinite Mario using A* path-finding, shown as a red planned path that updates as new obstacles appear. It won the Mario AI competitions and uses only on-screen information.

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.

A short demonstration of a crow using a purpose-built vending machine, in which the bird exchanges objects for rewards. The creator sells the machine as a kit.

Destin of Smarter Every Day learns to ride a bicycle whose steering is reversed, taking about eight months, and compares it with how his young son learned much faster. It illustrates knowledge versus understanding and brain plasticity in adults versus children.

Smarter Every Day host Destin Sandlin tries to hover a helicopter and finds it very hard. The video shows how the constant coordinated corrections across several control axes feel at first and how learning makes them automatic.

A short demo of the Deep Visualization Toolbox, which shows the activations inside a convolutional neural network as it processes live camera input. Viewers see individual units responding to edges, faces and text.

Short footage of the General Electric Cybernetic Anthropomorphous Machine, or Walking Truck, a 1960s quadruped vehicle operated by a human driver using hydraulic limbs. The uploader notes it predates Big Dog by decades.

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.

Karl Sims's 1994 demonstration of evolved virtual creatures: block-bodied creatures whose bodies and controllers are evolved through selection, mutation and recombination to swim, walk and compete.

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.

A six-minute journey through the layers of a neural network using Deep Dream, with each frame fed back into the network starting from random noise and the targeted layer changing every four seconds. It is set to downtempo music.

Matthias Wandel shows his wooden machine that adds binary numbers using marbles. It demonstrates computation with purely mechanical logic.

A restored 1994 video of Karl Sims' research on evolved virtual creatures, where simulated block creatures are bred through artificial evolution to swim, walk, follow and compete. It is a landmark demonstration of genetic algorithms in physics simulation.

A short promotional video of a 5-axis CNC machine milling an elaborate helmet, made by DAISHIN SEIKI with a DMG machine and hyperMILL CAM software. It shows what 5-axis machining can produce.

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.

Mike Boyd takes up Smarter Every Day's challenge to learn to ride the Backwards Brain Bike, a bicycle whose steering is inverted, and rides 50 meters. It shows how hard it is to unlearn a motor skill.

GeoGuessr pro Rainbolt plays head-to-head against an AI built by Stanford students that guesses locations from street-view images. The video shows the AI repeatedly beating him.

Dave Ackley demonstrates the Demon Horde Sort, an inherently robust sorting machine running in his Movable Feast Machine simulator. This is the uncut version with all details and side thoughts.

A demo of the Symbolics Graphics Division's S-Packages, a Lisp-based 3D color graphics and animation system from the 1980s. It was later used in developing for the Nintendo 64.

Kyle Hill of Because Science explains and demonstrates, using real cards, how Magic: The Gathering can be used to build a Turing machine, a computer inside the card game.

Dave Ackley presents robust-first computing and the ULAM programming language for the Movable Feast Machine, a cellular-automata-like architecture. It was a short video for the Future Programming Workshop 2015.

A 1970 demonstration of W. Timothy Gallwey, author of The Inner Game of Tennis, teaching a complete beginner to play tennis in about ten minutes. He chats with her, feeds balls and gives positive feedback instead of instruction.

Arthur Ganson's kinetic sculpture chains twelve 1:50 worm gear reductions so the final gear, embedded in concrete, would take over two trillion years to turn once.

A five-minute SuperMemo demo of incremental reading: importing a Wikipedia article on nutrition, extracting passages, making cloze deletions and finishing the item. It lists the keyboard shortcuts used.

A 47-minute restoration of a 1920s IBM computing cheese cutter, a machine with parts patented between 1901 and 1907. The video covers the restoration work and explains why it is a computing cheese cutter.

A promotional video from Oxbo showing its blueberry and raspberry harvesting machines in operation. It demonstrates mechanical berry harvesting at commercial scale.

A review of the Symbolics Space Cadet keyboard, with its Honeywell Hall effect switches, including how it sounds and feels, and a typing demonstration. It is part of a series of vintage keyboard reviews.

A short animation illustrating the proposed nanofactory concept, where nanomachines assemble atomically precise parts into larger products. It depicts how such a system might build macroscopic goods from raw materials and energy.

An award-winning 3D animation by XVIVO for Harvard's BioVisions showing the molecular machinery inside a cell as a white blood cell responds to a stimulus.