Evolutionary optimization of echo state networks: multiple motor pattern learning

Titelaufnahme

Titel
Evolutionary optimization of echo state networks: multiple motor pattern learning
Verfasser
Krause, André Frank ; Dürr, Volker ; Bläsing, Bettina ; Schack, Thomas
Erschienen
2010
Sprache
Englisch
Dokumenttyp
Konferenzband
Schlagwörter
Echo State Network / Neural network / motor pattern
ISBN
978-989-8425-03-4
URN
urn:nbn:de:0070-pub-16813780
DOI
10.5220/0003027500630071

Zugriffsbeschränkung

Links

Dateien

Klassifikation

Abstract

Echo State Networks are a special class of recurrent neural networks, that are well suited for attractor based learning of motor patterns. Using structural multiobjective optimization, the tradeoff between network size and accuracy can be identified. This allows to choose a feasible model capacity for a follow-up full weight optimization. Both optimization steps can be combined into a nested, hierarchical optimization procedure. It is shown to produce small and efficient networks, that are capable of storing multiple motor patterns in a single net. Especially the smaller networks can interpolate between learned patterns using bifurcation inputs.

Statistik