machine learning

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

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Andrej Karpathy, then Tesla's head of AI, presents at ScaledML 2020 on how Tesla builds full self-driving using vision-based neural nets and fleet data collection. He covers training custom detectors and neural nets gradually replacing traditional code.

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.

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.

Jim Keller's talk at the 2020 Scaled Machine Learning conference on Moore's Law in the age of AI chips. He compares scalar, vector and GPU-style parallel approaches to computation.

Dragan Djuric presents Clojure libraries for GPU and numerical computing, including ClojureCL, ClojureCUDA and Neanderthal. He shows how a dynamic REPL workflow can be combined with low-level hardware acceleration for machine learning and data science.

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.

Ilya Sutskever gives a Simons Institute talk on why neural networks generalize, framing learning as finding short descriptions, like compression. It was part of the Large Language Models and Transformers program.

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.

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.

Andrej Karpathy gives a one-hour general-audience introduction to large language models, covering what they are, how they are trained, comparisons to operating systems, and security challenges such as jailbreaks.

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.

Conal Elliott presents his paper on automatic differentiation, deriving a simple, generalized AD algorithm from a natural specification. Varying the representation of derivatives yields forward and reverse mode algorithms that avoid the complexity and statefulness of backpropagation.

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.

Andrej Karpathy walks through how GPT assistants are trained, from tokenization and pretraining to supervised finetuning and RLHF, and gives practical prompting strategies and a view of the tooling ecosystem.

Andrej Karpathy, then Tesla's head of AI, gives a CVPR 2021 workshop keynote on how Autopilot's neural networks work. A large part covers the move to a vision-only stack, including why radar was dropped and how vision produces depth estimates.

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.