Johnsonetal2016ArtLife.pdf (2.09 MB)
Active shape discrimination with compliant bodies as reservoir computers
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 HusbandsCompliant 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 LifeISSN
1064-5462Publisher
Massachusetts Institute of Technology PressExternal DOI
Issue
2Volume
22Page range
241-268Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2016-04-18First Open Access (FOA) Date
2019-03-05First Compliant Deposit (FCD) Date
2016-04-18Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC