Kiefer, Chris (2018) 10K video. [Performance]

HTML Restricted to SRO admin only Download (63kB)

Abstract

10000 neural oscillators conspire to make a bad approximation of a one second video loop, while their internal networks are stretched and twisted by their own sound and their neighbours.

This is an improvised performance, where a video is resynthesised by an ensemble of neural conceptor networks, each of which has learnt (with varying degrees of success) to approximate the behaviour of an individual pixel in the original. The ghostly result is manipulated live, to send this mass of miniature feedback systems into collective overdrive.

Item Type:	Performance
Keywords:	audiovisual, performance, machine learning
Schools and Departments:	School of Media, Film and Music > Music
Research Centres and Groups:	Centre for Research in Creative and Performing Arts
Subjects:	M Music. Literature on music. Musical instruction and study > M Music > M0005 Instrumental music > M1470 Aleatory music. Electronic music. Mixed media Q Science > Q Science (General) > Q0300 Cybernetics Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User:	Chris Kiefer
Date Deposited:	05 Apr 2018 11:11
Last Modified:	05 Apr 2018 11:11
URI:	http://srodev.sussex.ac.uk/id/eprint/74835

View download statistics for this item

📧 Request an update