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.

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.

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.

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.