classical

Colin Smith introduces Structure and Interpretation of Classical Mechanics and his Clojure port, sicmutils. He shows how higher-order functions and a symbolic algebra system can represent Lagrangian mechanics.

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.

Emily Shea explains how repetitive strain injury pushed her to program by voice using speech recognition (Talon), and gives a live coding demo. She argues voice-driven development can be pain-free, efficient and enjoyable.

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.

Luis von Ahn, creator of CAPTCHA and reCAPTCHA, explains how small contributions from many people online can digitize books. He then introduces Duolingo as a way to translate the web while people learn languages.

A short conference talk from !!Con 2017 in which Kevin Chen explains the HDR imaging algorithm from a foundational paper, framing it as a system of linear equations, and implements it in a Microsoft Excel spreadsheet. No prior image processing knowledge is needed.

David MacKay's 2007 Google Tech Talk presents Dasher, a text-entry system driven by continuous gestures and a language model, reaching about 35 words per minute with one finger and 25 hands-free. It explains the information-theory reasoning behind the design.

Physicist Geoffrey West speaks at an FQXi conference on time about complexity and scaling laws. He covers how metabolism, growth and lifespan scale across organisms and how the same mathematics applies to cities and companies.

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.

Retired Boeing Technical Fellow Doug McLean walks through common misconceptions in aerodynamics, drawing on his book Understanding Aerodynamics. He critiques popular explanations of wing lift and rocket thrust and argues for arguing from the real physics.

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.

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.

Robert Bussard's 2006 Google Tech Talk on inertial electrostatic confinement fusion, a compact approach he argued could be cheap and clean, using boron-hydrogen fuel without neutron radiation. It runs about 93 minutes and covers the physics, funding history and his proposed development path.

Reggie Watts performs at TED 2012, blending vocal looping, beatboxing, poetry and comedy across musical genres in a larger-than-life improvised set.

A PyCon 2012 talk by Kurt Grandis on building an automated water-squirting turret that uses Python and computer vision to detect and drive off squirrels from a bird feeder.

Part 2 of the IROS 2011 keynote by Sebastian Thrun and Chris Urmson on Google's self-driving car. It shows how the car perceives its surroundings with a lidar point cloud and recognizes traffic lights and pedestrians. The audio is poor because it was recorded on a pocket camcorder.

A 2015 talk by David Deutsch with slides and audio about constructor theory and how physics, in particular the many-worlds interpretation, can be framed without probability.

Pokey Rule presents Cursorless, a spoken language designed for editing code by voice, built on tree-sitter parsing with smart structural and simple token-level primitives. The talk is from Strange Loop 2023.

Luis von Ahn, creator of CAPTCHA and reCAPTCHA, presents Duolingo at TEDxCMU 2011. The idea is to have millions of people translate the web for free while learning a language, an example of human computation.

Mobileye co-founder and CTO Amnon Shashua explains what goes into sensing for autonomous driving and whether end-to-end deep learning can work for it. He argues for decomposing the problem.

Theoretical physicist Nima Arkani-Hamed gives a public talk on why spacetime may not be fundamental and what might replace it, including newer approaches to scattering amplitudes.

A 2006 Google TechTalk in which Luis von Ahn introduces human computation, using people's effort to solve problems like image recognition that computers cannot yet handle. It covers games with a purpose and related ideas such as CAPTCHAs.

Andrej Karpathy's CVPR 2021 presentation on Tesla's Autopilot, covering its vision-based approach, sensor choices and the scale of Tesla's deep learning compute cluster. This upload is a lower-quality copy of the talk.

Ramesh Raskar presents femto-photography, a technique that captures a trillion frames per second, fast enough to show light itself moving through a scene. He discusses possible uses such as cameras that see around corners or inside the body.

Lawyer and musician Damien Riehl argues that music is math with a finite number of melodies, and describes how he and programmer Noah Rubin generated every possible melody and released them under CC0 to avoid accidental infringement claims.

The 2016 Isaac Asimov Memorial Debate, moderated by Neil deGrasse Tyson, in which a panel of physicists and philosophers debates whether the universe is a simulation. Participants include David Chalmers, Zohreh Davoudi and James Gates.

Tom Gally, a former professional translator and University of Tokyo professor, discusses in March 2023 whether GPT-4 and similar models could translate literary and popular fiction. He gives his assessment of Japanese-to-English quality.

Berkeley neuroscientist Jack Gallant shows how fMRI brain mapping can be used to decode what a person sees, with visualizations of brain activity and its implications.

A HOPE XI talk on programming by voice with open source speech recognition. The speaker writes Linux systems code by voice and describes building custom voice grammars as an alternative to the keyboard for programmers with repetitive strain injuries.

An 88-minute Microsoft Research talk that explains how quantum computers beat classical ones using basic linear algebra, qubits, superposition and gates. It works through the Deutsch oracle problem and ends with entanglement, teleportation and a live demo.