University of Sussex
Browse
Johnsonetal2016ArtLife.pdf (2.09 MB)

Active shape discrimination with compliant bodies as reservoir computers

Download (2.09 MB)
Version 2 2023-06-12, 06:38
Version 1 2023-06-09, 00:55
journal contribution
posted on 2023-06-12, 06:38 authored by Chris JohnsonChris Johnson, Andy PhilippidesAndy Philippides, Phil HusbandsPhil Husbands
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.

Funding

INSIGHT-II Darwinian Neurodynamics; G1087; EUROPEAN UNION; 308943

History

Publication status

  • Published

File Version

  • Published version

Journal

Artificial Life

ISSN

1064-5462

Publisher

Massachusetts Institute of Technology Press

Issue

2

Volume

22

Page range

241-268

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-04-18

First Open Access (FOA) Date

2019-03-05

First Compliant Deposit (FCD) Date

2016-04-18

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC