representation

Bret Victor's closing keynote at UIST and SPLASH 2014 argues that our tools for thinking ignore most of human sensory and motor capability. He sketches representations that engage more modalities beyond screens and keyboards.

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.

CGP Grey explains the Single Transferable Vote, a proportional ranked-ballot system, and why politicians have little incentive to adopt it. It is a short animated explainer of how multi-winner ranked voting works.

CGP Grey explains how the 2015 UK general election showed the flaws of first-past-the-post voting, with parties like UKIP winning many votes but few seats.

An NBC Today Show correspondent appears to row a canoe in deep storm floodwater, though the water is only about six inches deep. The uploader notes it is a misleading depiction rather than intentional fake news.

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.

CGP Grey explains Mixed-Member Proportional representation, the system used in New Zealand where voters get two votes. It covers how it differs from first-past-the-post.

An excerpt of the 2005 Harvard debate in which Steven Pinker gives his prepared case on biological sex differences and the under-representation of women in science. It covers cross-cultural patterns in preferences and abilities and the overlap between male and female distributions.

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.

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.

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.

A Last Week Tonight segment on how century-old Supreme Court decisions left U.S. territories such as Puerto Rico, Guam and American Samoa without meaningful representation. It mixes comedy with a history of their legal status.

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.

Swift compiler engineers explain how Swift implements generics using dictionary-passing with reified type metadata. They compare it with Java-style uniform representation and C++ or Rust monomorphization.

A compilation of the hacking scenes from the 1995 film Hackers, featuring flashy visualizations of computer intrusion.