Active shape discrimination with physical reservoir computers

Johnson, Chris, Philippides, Andrew and Husbands, Philip (2014) Active shape discrimination with physical reservoir computers. In: Sayama, Hiroki, Rieffel, John, Risi, Sebastian, Doursat, René and Lipson, Hod (eds.) Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems. MIT Press, Cambridge, MA, USA, pp. 178-185.

[img]
Preview
PDF - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (3MB) | Preview

Abstract

We present the first example of ‘minimally cognitive’ sensorimotor behaviour arising from a body as physical reservoir.
By revisiting an experiment introduced by Beer (1996)
and replacing the continuous-time recurrent neural network
(CTRNN) therein with networks of mass-spring-dampers we
demonstrate that bodies may be exploited for more than control
and pattern generation and take over some tasks which
were previously thought to require a central nervous system.

Item Type: Book Section
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Q Science > QP Physiology > QP0351 Neurophysiology and neuropsychology > QP0361 Nervous system
Related URLs:
Depositing User: Phil Husbands
Date Deposited: 05 Aug 2014 11:26
Last Modified: 05 Aug 2014 11:26
URI: http://sro.sussex.ac.uk/id/eprint/49479

View download statistics for this item

📧 Request an update