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

Hywel Williams

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

Hywel Williams

Research output: Contribution to conference › Paper

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 language	English
Publication status	Published - Sept 2005
Event	3rd International Symposium on Adaptive Motion in Animals and Machines - Technische Universität Ilmenau, Germany Duration: 25 Sept 2005 → 30 Sept 2005

Conference

Conference	3rd International Symposium on Adaptive Motion in Animals and Machines
Abbreviated title	AMAM 2005
Country/Territory	Germany
Period	25/09/05 → 30/09/05

Cite this

@conference{1164d55b257d48879b3df72794aa08a4,

title = "Homeostatic plasticity improves continuous-time recurrent neural networks as a behavioural substrate",

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.",

author = "Hywel Williams",

year = "2005",

month = sep,

language = "English",

note = "3rd International Symposium on Adaptive Motion in Animals and Machines, AMAM 2005 ; Conference date: 25-09-2005 Through 30-09-2005",

}

TY - CONF

T1 - Homeostatic plasticity improves continuous-time recurrent neural networks as a behavioural substrate

AU - Williams, Hywel

PY - 2005/9

Y1 - 2005/9

N2 - 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.

AB - 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.

M3 - Paper

T2 - 3rd International Symposium on Adaptive Motion in Animals and Machines

Y2 - 25 September 2005 through 30 September 2005

ER -