Evolutionary optimization of echo state networks : multiple motor pattern learning
Gespeichert in:
| Deutscher übersetzter Titel: | Evolutionäre Optimierung von Echo-State-Netzwerken : multiples Bewegungsmusterlernen |
|---|---|
| Autor: | Krause, André Frank; Dürr, Volker; Bläsing, Bettina; Schack, Thomas |
| Erschienen in: | Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; 17 - 18 June, 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, 15 - 18 June 2010 |
| Veröffentlicht: | Setúbal: INSTICC Press (Verlag), 2010, S. 63-71, Lit. |
| Format: | Literatur (SPOLIT) |
| Publikationstyp: | Sammelwerksbeitrag |
| Medienart: | Gedruckte Ressource |
| Sprache: | Englisch |
| Schlagworte: | |
| Online Zugang: | |
| Erfassungsnummer: | PU201104003999 |
| Quelle: | BISp |
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 multi-objective optimization, the trade-off 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. Verf.-Referat