Neural Abstractions

Lecture | April 13 | 6:30-8 p.m. |  Osher Theater, BAMPFA

 Tom White, Victoria University of Wellington School of Design

 Berkeley Center for New Media, Arts + Design, CITRIS and the Banatao Institute, Autolab

How do machines perceive the world? Tom White has investigated enabling computer vision systems to draw their own visual abstractions through the creation of abstract ink print artworks. Though these artificial vision systems are trained only on real world images, when forced to express themselves abstractly they are able to create simpler forms that match their internal representations. These prints are also understood universally across most AI systems trained to recognise the same objects. It’s art by AI, for AI. By giving the algorithms the ability to express themselves directly, we are better able to see the world through the eyes of a machine.

About Tom White

Tom White has been working with AI and drawing systems for 25 years. His early work on drawing frameworks at MIT led to influential toolkits that are still popular today - such as Processing and OpenFrameworks. He is a senior lecturer in computational design at Victoria University of Wellington School of Design, where he teaching creative coding and researches creative applications of modern AI techniques. Tom’s artwork focuses on how machines see the world: neural networks use a specially constructed drawing system to produce abstract ink prints that reveal their own visual abstractions.