predictive processing

The first lecture of Stanford's Natural Language Processing with Deep Learning course, taught by Chris Manning and Richard Socher. It introduces NLP and word vectors, including SVD, skip-gram, CBOW, negative sampling and word2vec.

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.

Neuroscientist Anil Seth gives a Royal Institution lecture on the science of consciousness. He separates conscious level, content and self, and argues that experience arises from the brain's predictive inference.

Samuel Falvo II live-codes a text preprocessor and blog engine in Forth over about an hour. It shows Forth's dictionary being snapshotted and restored in place of mutation, and how a small Forth system gets real work done.

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.

Andrew Adams, a Halide developer, presents the Halide language for image processing and tensor computation. The talk explains the separation of algorithm from schedule with illustrated examples of parallelism, locality and redundancy tradeoffs.

Technology Connections explains why the superheterodyne radio has its name and how mixing frequencies lets it tune stations well. It walks through the underlying wave phenomena and algebra and why the design solved a hard tuning problem.

David Sachs of InvenSense explains how gyroscopes, accelerometers and compasses work on their own and together, demonstrated on a modified Android handset. He covers sensor fusion algorithms and why rotation math such as Euler angles matters.

Boston Dynamics shows its Atlas humanoid robot performing a gymnastics and parkour routine, using optimization-generated motions and a model predictive controller.

3Blue1Brown's animated visual introduction to the Fourier Transform, showing how a signal breaks into frequency components.

Martin Kleppmann argues that databases are global shared mutable state and proposes treating them as an ever-growing log of immutable facts. Derived data such as caches, indexes and views is then built by stream processors like Apache Samza. The talk draws on Kafka and LinkedIn's experience with commit logs.

A lecture by Richard Feynman on how computers work, using the analogy of a filing clerk that becomes progressively dumber and faster. It also covers heuristics and how computers handle data and solve problems in finite time.

3Blue1Brown shows how the uncertainty principle arises from Fourier transforms. A wave packet cannot be narrow in both position and frequency, so the principle is a property of waves rather than of measurement.

MinutePhysics explains that computers store brightness nonlinearly, so blurring and blending colors in raw RGB gives wrong, dark results. It shows why mixed colors, such as in gradients, look off.

The first lecture in an 18-part series on digital photography from Marc Levoy's Stanford CS 178 course, recorded at Google in 2016. The series covers how digital cameras work and computational photography, with slides and assignments available on the course site.

Neuroscientist Karl Friston gives a 15-minute talk on the free energy principle, covering Markov blankets, Bayesian model evidence and global brain theories.

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.

MIT researchers show that sound can be recovered from silent video by analyzing tiny vibrations in objects such as a potato chip bag. It works even with consumer cameras by using rolling shutter.

A short 'How It's Made' television segment showing the industrial process of turning canola seed into cooking oil. It walks through pressing, solvent extraction and refining steps.

Jamie Oliver shows school kids how chicken nuggets are made by blending skin and mechanically reclaimed meat, as part of his school lunch campaign. The kids react with disgust.

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.

Rick Houlihan's AWS re:Invent 2018 deep dive on advanced DynamoDB design patterns. It covers index overloading, GSI sharding, composite keys, graph processing and transactions.

The full recording of Douglas Engelbart's 1968 demonstration, which introduced the mouse, hypertext, video conferencing, word processing, and real-time collaborative editing. It runs about 100 minutes.

Bret Victor's 2013 MIT Media Lab talk argues that the media we think with determine which thoughts are possible. He demos new representations for scientific papers, circuits, filters and signal processing.

Derren Brown's TV special in which he convinces a person he has a system for predicting horse race winners, demonstrating how survivorship bias and selective outcomes can fake predictive powers.

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.

An AWS re:Invent 2019 session for advanced DynamoDB users on design patterns used by large customers, including Amazon retail. It covers GSI sharding, index overloading, graph processing, composite keys and transactional workflows.