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.
|Publication status||Published - Sep 2005|
|Event||3rd International Symposium on Adaptive Motion in Animals and Machines - Technische Universität Ilmenau, Germany|
Duration: 25 Sep 2005 → 30 Sep 2005
|Conference||3rd International Symposium on Adaptive Motion in Animals and Machines|
|Abbreviated title||AMAM 2005|
|Period||25/09/05 → 30/09/05|