perception

Cognitive scientist Donald Hoffman argues in this TED talk that evolution shaped perception to track fitness rather than truth. He uses evolutionary simulations and the Australian jewel beetle as examples.

Neuroscientist Beau Lotto runs the audience through color and pattern illusions to show that perception is shaped by context and evolutionary history rather than being a direct readout of the world. The talk is playful and hands-on, and it argues that the brain interprets ambiguous signals.

Neuroscientist Anil Seth argues in this TED talk that perception is a controlled hallucination: the brain constantly predicts the world and our shared agreement is what we call reality. He also touches on the construction of the self.

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.

Philosopher Dan Dennett argues in a TED talk that we do not understand our own consciousness and that our brains often fool us. He uses perceptual examples, including a painting that invites the viewer to fill in detail.

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.

Chris Urmson, head of Google's self-driving car program, shows footage of how the car perceives the road and decides what to do. Examples include cyclist hand signals, school buses, police officers and complex intersections.

Joscha Bach's 35C3 talk offers an AI perspective on the soul, covering perception, mental representation, agency, consciousness and selfhood as things that can arise in a computational system like the brain.

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.

SciPy 2015 talk by Nathaniel Smith and Stefan van der Walt on choosing a new default colormap for Matplotlib. It covers why Jet misleads, how perceptual color spaces work, and how viridis was designed.

Michael Levin's NeurIPS 2018 talk on bioelectric computation outside the nervous system, showing how cell electrical networks shape development and regeneration. It covers morphological information processing in living tissue.

Gary Wilson's TEDxGlasgow talk argues that internet pornography hyperstimulates the brain's reward system and can cause symptoms that reverse when people stop. TED notes that several claims are not supported by respected academic studies.

A Google Tech Talk by sleep researcher Dr. William Dement on healthy sleep and performance. He argues sleep debt must be repaid and describes the three characteristics of healthy sleep.

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.

Chris Urmson's SXSW 2016 talk on Google's self-driving car project, covering 1.3 million self-driven miles and the gap between hype and reality. It shows sensor visualizations and playbacks of hard situations the cars met, and discusses failures such as the low-speed bus collision.

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.

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.

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.

Dr. Howard Schubiner presents his research that much chronic pain comes from learned neural pathways rather than structural damage, and outlines a treatment approach based on that view.

A short edited excerpt of Terence McKenna arguing that culture acts as an operating system for the mind, set to imagery and music. It touches on psychedelics and how they change thinking.

Moral philosopher James Flynn explains the Flynn effect, the steady rise of IQ scores across the 20th century. He argues the shift reflects a move toward abstract, hypothetical thinking as cognitively demanding professions grew.

Daniel Dennett gives a Royal Institution talk toward a unified theory of information, tying together evolution, learning and engineering. He argues that design can arise bottom-up through small steps without a designer.

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.

Neuroscientist Jill Bolte Taylor describes watching her own brain functions shut down during a massive stroke. She gives a first-person account of losing speech, motion and self-awareness.

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.

Tesla's roughly four-hour Autonomy Day investor event covers its in-house self-driving chip, vision-only approach, fleet data engine and robotaxi plans, with talks by Andrej Karpathy and others.

Berkeley sleep scientist Matthew Walker presents the science of sleep and dreams and how sleep affects health and lifespan, based on his book Why We Sleep.

Joscha Bach's 31c3 talk argues that the mind should be understood as an information-processing system and that even the physical universe can be seen as computational. It tours the philosophy underlying artificial intelligence and cognitive science.

Developmental and synthetic biologist Michael Levin speaks at a Harvard Extension student event on bioelectricity, body intelligence and regenerative medicine. He discusses how cell electrical networks guide growth and form.

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.

Joscha Bach's 32C3 talk applies computational theories of mind to questions of meaning, emotion, and love, asking how computation can explain irrational-seeming human experience.

Sebastian Seung's TED talk introduces the connectome, the map of neural connections he argues defines each person. He explains how mapping it could change how we understand brains and minds.

UCLA professor Dario Nardi presents brain-imaging research suggesting that different Myers-Briggs personality types use their brains in different ways. He discusses how each type can reach a state of creative flow. It is aimed at a general audience.

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.

David Rock gives a Google Tech Talk based on his book Your Brain at Work, using neuroscience to explain why focus and productivity are hard at the office. He gives strategies for managing mental energy and distraction.

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.