Homeostatic plasticity improves continuous-time recurrent neural networks as a behavioural substrate

Hywel Williams

Research output: Contribution to conferencePaper

Abstract

Homeostatic plasticity is applied to continuous-time recurrent neural networks. It is observed to make networks more sensitive, improve signal propagation and increase the likelihood of autonomous oscillations. Evolutionary experiments with a simulated robot show that in some circumstances homeostatic plasticity improves evolvability of good control networks, but in others it makes good controllers less easy to evolve.
Original languageEnglish
Publication statusPublished - Sep 2005
EventProceedings of 3rd International Symposium on Adaptive Motion in Animals and Machines (AMAM 2005) - Technische Universität Ilmenau, Germany
Duration: 25 Sep 200530 Sep 2005

Conference

ConferenceProceedings of 3rd International Symposium on Adaptive Motion in Animals and Machines (AMAM 2005)
CountryGermany
CityTechnische Universität Ilmenau
Period25/09/0530/09/05

Cite this