mach-e

The first episode of Google's Machine Learning Recipes series. It introduces machine learning and builds a first supervised-learning classifier in about six lines of Python using scikit-learn.

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.

An episode of Tim Hunkin's The Secret Life of Machines that explains how a washing machine works, using models, cut-aways and animations. It was first aired in 1988.

Machine Thinking argues the 1751 machine, a metal-cutting lathe associated with Vaucanson, triggered the biggest explosion of wealth in history by enabling precise manufacturing of other machines.

The first episode of Clickspring's series building a John Wilding skeleton clock from raw stock in a home machine shop. It covers making the frames along with the tools needed for the job.

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.

Chris Lattner and Brennan Saeta present Swift for TensorFlow at the TensorFlow Dev Summit 2019, covering language-integrated automatic differentiation and tooling for machine learning in Swift.

Ali Rahimi accepts the NIPS 2017 Test of Time Award and argues that machine learning has become alchemy, with practice running ahead of understanding.

Machine Thinking traces where mechanical precision comes from, from flat surface plates and the three-plate method up through lathes and early measuring tools. It is the first in a series on recreating the first micrometer.

Part 1 of an episode of the British educational TV series The Secret Life of Machines, about how vacuum cleaners work and their history. It mixes humor with explanation of household technology.

Wintergatan's video of the Marble Machine, a hand-built music instrument that plays a song using about 2000 marbles on a mechanical clockwork-style mechanism.

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.

The first lecture of Caltech's CS 156 Machine Learning course by Yaser Abu-Mostafa, introducing the learning problem and supervised, unsupervised and reinforcement learning. It is one of 18 lectures in the Learning from Data course.

A Computer History Museum oral history with Avie Tevanian covering his math talent, work on the Mach microkernel at CMU, joining NeXT, leading NEXTSTEP development and the 1996 Apple acquisition.

John Oliver's Last Week Tonight segment on US voting machines, covering how they work, their security weaknesses, and how elections could be made more secure.

Dan Gelbart shows his home-built air bearing CNC lathe and grinder, which reaches about 1 micron accuracy. He demonstrates the machine and its parts.

Geoffrey Hinton's Google Tech Talk linking machine learning to biology, explaining dropout as a form of model averaging and why sexual reproduction and stochastic spiking neurons may prevent overfitting.

Cliff Click, author of HotSpot's JIT compiler, shares hard-won advice for people writing virtual machines at the VMSS16 workshop. Topics include interpreters, JITs and performance lessons.

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.

James Mickens's humorous USENIX Security keynote argues that improving security and trusting opaque technology like machine learning is far harder than the industry admits.

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 GDC 2018 talk by Valve's John McDonald on VACNet, a deep learning system that analyzes CS:GO gameplay to detect cheaters. It covers how the model is trained on human-reviewed Overwatch cases and how its output feeds human moderation.

Ali Rahimi's NIPS 2017 Test-of-Time award talk, in which he argues that modern machine learning has become alchemy, working without being rigorously understood. He calls for more rigor and understanding in the field.

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

OK Go's music video for This Too Shall Pass, featuring a huge Rube Goldberg machine built in a warehouse in Los Angeles with Syyn Labs. The band interacts with the contraption in one continuous take.

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.

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.

The first lecture of David Silver's reinforcement learning course, introducing the field and its basic concepts. The course follows the Sutton and Barto textbook.

In this 2019 GDC talk, Alex Schwartz and Ziba Scott explain how they flooded the app stores with over 1,500 auto-generated slot machine games to find the lowest bar for success. They tour the dark side of the mobile app market.

George Hotz of Comma AI gives a 2017 conference talk on lessons from building a self-driving system. He argues about how driving should be defined and why the common approach to autonomous vehicles is flawed.

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.

The first lecture of David MacKay's Cambridge course on information theory, pattern recognition and neural networks. It introduces the core ideas of his book Information Theory, Inference, and Learning Algorithms.

Lex Fridman interviews Jeff Hawkins, founder of Numenta and author of On Intelligence, about the Thousand Brains Theory and reverse-engineering the neocortex. They also cover Hierarchical Temporal Memory and brain-inspired AI architectures.

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.

Chris Stucchio presents the ethical principles behind algorithmic decision making and shows with examples from lending, criminology and education that they cannot all be satisfied at once. The talk frames AI fairness as a set of quantitative tradeoffs.

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.

Jeff Hawkins presents his view that the neocortex works on principles different from traditional computers. He describes sparse distributed representations and how they are learned, then shows how Numenta applies them to predict from high-velocity data streams.

A Google Tech Talk by Laurens van der Maaten, co-creator of t-SNE, on visualizing high-dimensional data by mapping it to two dimensions. It explains how the technique works and how it compares with other visualization approaches.

An excerpt of Richard Feynman's 1985 lecture Q&A about whether machines can think. He discusses the difficulty of defining what computers can never do and compares machine intelligence to machines that don't copy animals.

Andrej Karpathy's Databricks talk on Software 2.0, the shift from human-written code to code produced by neural network training. It covers how developer work moves toward curating datasets, the advantages and challenges, and opportunities for new tooling.