machine learning history

The first lecture of Andrew Ng's Stanford CS229 Machine Learning course, giving an overview of the course. It introduces supervised and unsupervised learning, learning theory and reinforcement learning.

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.

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 Learning Street Talk interviews Paul Lessard about Categorical Deep Learning, which uses category theory and monads to make neural network architectures more interpretable and composable. They also discuss neural networks' limits in reasoning and unbounded computation.

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 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.

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.

Valve's John McDonald presents at GDC 2018 on how Valve uses deep learning (VACnet) to detect cheaters in Counter-Strike: Global Offensive. He covers training on human-reviewed replays and how model output is confirmed by manual review.

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.

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.

Steve Blank's Computer History Museum lecture argues that Silicon Valley's roots lie in WWII radar and electronic warfare work, Stanford's Fred Terman and Cold War military funding rather than the semiconductor alone.

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.

A Computer History Museum oral history of Chuck Peddle, the engineer behind the 6502 and the Commodore PET, covering his career from GE through Motorola and MOS Technology. It runs nearly four hours.

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

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.

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.

A Computer History Museum oral history panel with four 3dfx founders on the company's rise with Voodoo Graphics and Glide, and its fall into bankruptcy. It runs about two and a half hours.

A Computer History Museum oral history interview with Dave Cutler, covering his youth, early work on operating systems at DuPont and Digital Equipment, and his path toward VMS and Windows NT. This is part one of a long-form interview.

Part two of a Computer History Museum oral history with Gary Davidian, covering his work on the 68000 emulator for PowerPC at Apple, Power Computing, clean-room contracting and later performance optimization work. It is nearly three hours long.

Grady Booch interviews John Backus, who led the IBM team that created FORTRAN in 1957, for the Computer History Museum in 2006. Backus describes the development of the first successful high-level language and its compiler. The interview runs 88 minutes.

A Computer History Museum oral history with Bill Mensch, designer of the 6502 and 65816, covering his path from a Pennsylvania farm through Motorola and later work.

A two-hour Computer History Museum oral history interview with Bjarne Stroustrup, conducted by Paul McJones in 2015. It covers his youth, education at Aarhus and Cambridge, his career at Bell Labs and elsewhere, and the design and evolution of C++.

Computer History Museum oral history of Steve Naroff, an engineer at Stepstone, NeXT and Apple who worked on Objective-C. This first session covers his childhood, music background and early career.

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.

Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.

The first lecture of N J Wildberger's History of Mathematics course, starting with Pythagoras' theorem and following Stillwell's text. It emphasizes the flow of ideas over proofs.

The first episode of Crash Course World History, in which John Green covers the shift from hunting and gathering to agriculture and how it shaped civilization. It is delivered fast and with jokes.

Tom Scott-style absurdist research by tom7 for SIGBOVIK 2021, using machine learning to discover letterforms that are 'uppercaser' than uppercase A and lowercaser than lowercase. It is a comedic, technically inventive deep dive with fonts and a paper.

A long documentary-style video arguing that slavery in the US effectively continued through convict leasing and the prison system until around 1942. It covers the constitutional carveout and the history of neoslavery.

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.

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.

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

First part of a four-part video history of Japan's electronics industry, covering the birth of the transistor and the rise of Japanese semiconductors. It appears to draw on NHK documentary material.

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.

An ICFP 2015 keynote on the history of Standard ML, covering its ideas, principles and culture. It traces ML from Strachey, Landin and Milner through SML's development and its interplay with OCaml.

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.

Kirk McKusick gives a narrative history of the Berkeley Software Distributions at MeetBSD California. He covers how BSD originated and evolved, including the origin of the networking releases.

Bill Wurtz's fast, comedic and musical run through the whole history of Japan in nine minutes.