computer vision

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.

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.

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.

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.

Michael Steil and Christian Hessmann's 34C3 talk explaining the Apollo Guidance Computer end to end: hardware design, operating system, and mission software.

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.

A full-day recording of the University of Utah computer science department's 50th anniversary event with panels, keynotes and talks by alumni and pioneers. It includes Ivan Sutherland's presentation on single flux quantum electronics.

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.

David Patterson's talk on the history of computer architecture, from RISC and superscalar designs to the end of Dennard scaling and Moore's Law. It argues that domain-specific architectures and open instruction sets open a new golden age.

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 Strange Loop 2019 talk by Aaron Cummings on the computing systems aboard Voyager 1 and 2, which control the spacecraft and record and return data decades after launch in 1977.

Joe Armstrong's GOTO 2018 talk contrasts the problems computer scientists study with the problems users have. He revisits forgotten great ideas such as tuple spaces, flow-based programming, Xanadu and Unix pipes, with anecdotes.

Brian Troutwine's Code Mesh 2015 talk on the Apollo Guidance Computer. It covers the AGC's design, core rope memory, its interrupt and software behavior, and the pioneering engineering effort behind it.

A Talks at Google visit by Douglas Engelbart, inventor of the mouse. He presents his lifelong aim of augmenting collective human intelligence, followed by a Q&A.

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.

Ted Nelson's short eulogy for Douglas Engelbart, delivered at the Computer History Museum in 2013, reflecting on his friend and Engelbart's ideas.

Tesla's full AI Day 2022 presentation, covering the Tesla Bot hardware and software, Full Self-Driving planning and perception, the occupancy network, data labeling, simulation and Dojo training infrastructure.

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.

Seymour Cray's only surviving recorded talk, introducing the Cray-1 supercomputer in 1976. He describes the machine's design, including its vector architecture and cooling through the frame.

A 1992 MIT Sloan talk and Q&A by Steve Jobs, then CEO of NeXT, covering NeXT's strategy, co-creating Apple, his ouster, and the value of direct experience. It ranges across technology, business and career advice.

Tesla's 2021 AI Day presentation covering vision, planning and control, auto-labeling, simulation, the Dojo training hardware and the Tesla Bot announcement, followed by a Q&A.

Recording of the January 1984 Boston Computer Society meeting where Steve Jobs unveiled the Macintosh. It is followed by a panel Q&A with core Mac team members such as Andy Hertzfeld, Bill Atkinson and Steve Capps.

A HOPE09 talk on how modern computer chips are manufactured, from 22nm transistors to ultra-clean fabs and the tricks used to pattern tiny features with light. It frames chipmaking as hacking electrical engineering and physics.

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.

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.

A short !!Con 2016 talk by blind developer Sina Bahram on how he uses a computer and writes code with a screen reader at about 1,000 words per minute. He plays how common interfaces sound and challenges the audience to go a day using only the keyboard.

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.

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.

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.

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.

Megan McArdle's AEI Vision Talk 'Capital and Poverty' argues that social and financial capital work differently in low-income communities, and that this explains barriers to reaching the middle class.

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.

Alan Kay's 1997 OOPSLA keynote argues that the computer revolution has not really happened yet, reflecting on how computing, objects and the web fall short of their potential.

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.

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.

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.

Sasa Juric explains what makes Erlang and Elixir suited to server-side systems, focusing on the BEAM concurrency model rather than syntax or ecosystem. He demonstrates processes, supervision, and fault tolerance.