machine learning math

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

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.

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.

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.

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.

Conrad Wolfram argues that the part of math taught in schools, hand calculation, is tedious and mostly irrelevant to real mathematics. He proposes teaching math through computer programming so students can tackle real problems.

Matt Parker's Royal Institution talk based on his book Humble Pi, covering everyday mathematical mistakes and spurious patterns that went wrong in engineering and software. It mixes stand-up comedy with stories of coincidence and error.

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.

Mathematician Kevin Buzzard explains why he believes the Lean theorem prover will shape the future of mathematics, and describes digitizing his university curriculum in Lean with undergraduates, plus the cultural challenges.

Veritasium's Derek Muller gives a Perimeter Institute livestream on how AI might change teaching and learning. He draws on past technology shifts and cognitive science to argue that learning requires effortful repetition.

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.

Hans Rosling makes the case that the washing machine was the greatest invention of the industrial revolution. Using Gapminder graphics, he shows how electricity and economic growth free up time for reading and learning.

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.

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 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.

Peter Norvig's 2007 Google talk on theorizing from data, covering what huge datasets can do for language understanding, translation, information extraction and inference. It argues that more data often beats cleverer models.

Jose Valim introduces Nx, the project bringing numerical computing to Elixir, covering multi-dimensional tensors, automatic differentiation and JIT compilation to CPU and GPU.

Mathematician Hannah Fry's TED talk on patterns in dating and mate-seeking, including optimal stopping and three math-backed tips for finding a partner.

David Ditzel of Esperanto Technologies presents their massively parallel, energy-efficient RISC-V processors at the 7th RISC-V Workshop in 2017. It covers the high-performance many-core design aimed at machine learning.

Dan Bornstein's Google I/O 2008 talk on the internals of Dalvik, the virtual machine that runs Android code. It covers the motivation for its design, the dex format and its register-based interpreter, plus tips for writing code that suits the platform.

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.

Matt Parker gives a hands-on Royal Institution talk on how four-dimensional shapes appear in a 3D world, with props like straw frames, Mobius strips and a knitted hat. It is a playful general-audience tour of the fourth dimension.

Sal Khan of Khan Academy argues that schools push students forward with gaps in their foundations, and that students should instead master concepts at their own pace. He compares it to building a house on an unfinished foundation.

Bryan Cantrill of Oxide Computer Company gives a Stanford EE380 talk on rethinking the server. He argues that hyperscaler-style rack-scale machines with open firmware, RISC-V and Rust should be available to everyone, not just the giants.

A talk by Yuri Iozzelli at a WebAssembly meetup on CheerpX, an x86 virtual machine running in the browser. It uses a JIT compiler that emits WebAssembly at runtime to run real native applications. It covers the architecture and demos such as porting a multiplayer C++ game.

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.

Kathy Sierra's Fluent 2015 keynote on the one metaskill for developers: the ability to come up to speed quickly and stay there. She covers how people learn, cognitive resources versus willpower, and building skill.

Simon Knowles, co-founder and CTO of Graphcore, talks about "intelligence processors", chips designed specifically for machine learning. The talk was given at the RAAIS 2017 summit and covers Graphcore's architecture.

Peter Norvig, then Director of Research at Google, talks at Startup School 2008 about leveraging large amounts of data and about technical challenges in Google projects such as image search. A central idea is that data can beat hand-written programming.

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.

UC Berkeley EECS colloquium by OpenAI's John Schulman on reinforcement learning from human feedback. He covers why RL helps with truthfulness, hallucination, and the limits of behavior cloning.

Kalman Reti, one of the last Symbolics developers, gives a roughly hour-long talk on Symbolics Lisp machines. It covers the machines and their environment from an insider's perspective.

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.

Joseph Henrich's Talks at Google presentation of his book. He argues that human success comes from collective brains and cultural learning across generations rather than individual intelligence.

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.

Gerald Jay Sussman speaks at Dan Friedman's 60th birthday celebration about how programming helps formulate and clarify ideas. He argues that ambiguous mathematical notation hinders understanding.

Chuck Moore, inventor of Forth, presents GreenArrays' 144-core asynchronous chip at Strange Loop 2013. He explains how idle cores draw almost no power and how tight code minimizes energy use.