ear training

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.

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.

Yosh trains a reinforcement learning agent to drive Trackmania until he can no longer beat it. The video explains how the training works and the design choices involved.

A 1930s Chevrolet training film explaining the principles and development of the differential gear. It builds the idea step by step from first principles to the finished mechanism.

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

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 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.

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.

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.

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.

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.

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.

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

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.

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

Lesson 1 of fast.ai's Practical Deep Learning for Coders, taught by Jeremy Howard. It takes coders from running code in a Jupyter notebook straight into training a real image model.

David and Ben Crystal introduce the Original Pronunciation production of Shakespeare and show what it reveals about the history of English, including puns and rhymes lost in modern speech.

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.

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.

Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.

The first lecture of Stanford's Natural Language Processing with Deep Learning course, taught by Chris Manning and Richard Socher. It introduces NLP and word vectors, including SVD, skip-gram, CBOW, negative sampling and word2vec.

Bill Dally of NVIDIA gives a Hot Chips 2023 keynote on the challenges of building hardware for deep learning. He traces how GPUs have been adapted for machine learning, especially training.

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.

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.

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.

The final lecture of Richard Hamming's Learning to Learn course, from 1995, based on his well-known talk 'You and Your Research'. It covers how to do important work and build a career.

Top Gear segment in which Hammond and May try to turn a Reliant Robin into a space shuttle. Launching is easy, but landing it safely is the problem.

The first chapter of 3Blue1Brown's Essence of Linear Algebra series, introducing vectors with animated geometric visuals. It begins a series that builds intuition for linear algebra from the basics.

The first lecture of Gilbert Strang's MIT 18.06 Linear Algebra course, covering the geometry of linear equations. It opens a full 35-lecture university course.

Richard Hamming's 1995 recording of his talk 'You and Your Research', drawn from his graduate engineering course. He discusses how great scientists pick important problems and build careers, drawing on his years at Bell Labs.

A five-minute preview of 3Blue1Brown's Essence of Linear Algebra series, which uses animation to build geometric intuition for topics from a standard linear algebra course.

A 10-minute 3Blue1Brown chapter explaining the determinant as the factor by which a linear transformation scales area or volume. It builds the idea geometrically with animations before any formulas.

Chris Lonsdale presents a TEDx talk on how adults can learn a language in about six months, centering on immersion, comprehensible input and a practical learning methodology.

In this TEDxBerlin talk, environmental activist Michael Shellenberger explains why he changed from opposing nuclear power to advocating it, after looking at the evidence on Chernobyl, Fukushima and air pollution.

Kurzgesagt compares how many people nuclear accidents have killed against other energy sources. It walks through the worst nuclear accidents and puts their death tolls in context per unit of energy.

A professor from Illinois compares the cost of building, fueling and operating a nuclear plant against a natural gas plant, using visual charts. It shows how construction time and interest rates dominate, when the investment pays off and when costs cross over.

Harvard Belfer Center lecture by Matthew Bunn explaining how nuclear bombs work, including fission and fusion weapons and which parts of bomb-making are hard. It is part 1 of 2 in the Nuclear 101 series.

hbomberguy investigates the modern flat earth movement and why people come to believe it. The video treats the community with a measured, humorous tone and looks at the social causes behind the belief.