Active shape discrimination with compliant bodies as reservoir computers

Johnson, Chris, Philippides, Andrew and Husbands, Philip (2016) Active shape discrimination with compliant bodies as reservoir computers. Artificial Life, 22 (2). pp. 241-268. ISSN 1064-5462

[img] PDF - Published Version
Download (2MB)
[img] PDF (preprint of journal paper) - Submitted Version
Download (6MB)


Compliant bodies with complex dynamics can be used both to simplify control problems and to lead to adaptive reflexive behavior when engaged with the environment in the sensorimotor loop. By revisiting an experiment introduced by Beer and replacing the continuous-time recurrent neural network therein with reservoir computing networks abstracted from compliant bodies, we demonstrate that adaptive behavior can be produced by an agent in which the body is the main computational locus. We show that bodies with complex dynamics are capable of integrating, storing, and processing information in meaningful and useful ways, and furthermore that with the addition of the simplest of nervous systems such bodies can generate behavior that could equally be described as reflexive or minimally cognitive.

Item Type: Article
Keywords: morphological computation, reservoir computing, adaptive behaviour, active perception, minimal cognition
Schools and Departments: School of Engineering and Informatics > Informatics
Q Science > QP Physiology > QP0351 Neurophysiology and neuropsychology > QP0361 Nervous system
Related URLs:
Depositing User: Phil Husbands
Date Deposited: 18 Apr 2016 10:59
Last Modified: 23 Nov 2020 16:22

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
INSIGHT-II Darwinian NeurodynamicsG1087EUROPEAN UNION308943