Evolutionary optimization of echo state networks: multiple motor pattern learning
Krause AF, Dürr V, Bläsing B, Schack T (2010)
In: Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010. 63-71.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Einrichtung
Abstract / Bemerkung
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.
Stichworte
Echo State Network;
Neural network;
motor pattern
Erscheinungsjahr
2010
Titel des Konferenzbandes
Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010
Seite(n)
63-71
Konferenz
6th International Workshop on Artificial Neural Networks and Intelligent Information Processing (ANNIIP 2010)
Konferenzort
Funchal, Madeira
ISBN
978-989-8425-03-4
Page URI
https://pub.uni-bielefeld.de/record/1681378
Zitieren
Krause AF, Dürr V, Bläsing B, Schack T. Evolutionary optimization of echo state networks: multiple motor pattern learning. In: Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010. 2010: 63-71.
Krause, A. F., Dürr, V., Bläsing, B., & Schack, T. (2010). Evolutionary optimization of echo state networks: multiple motor pattern learning. Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010, 63-71. https://doi.org/10.5220/0003027500630071
Krause, André Frank, Dürr, Volker, Bläsing, Bettina, and Schack, Thomas. 2010. “Evolutionary optimization of echo state networks: multiple motor pattern learning”. In Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010, 63-71.
Krause, A. F., Dürr, V., Bläsing, B., and Schack, T. (2010). “Evolutionary optimization of echo state networks: multiple motor pattern learning” in Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010 63-71.
Krause, A.F., et al., 2010. Evolutionary optimization of echo state networks: multiple motor pattern learning. In Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010. pp. 63-71.
A.F. Krause, et al., “Evolutionary optimization of echo state networks: multiple motor pattern learning”, Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010, 2010, pp.63-71.
Krause, A.F., Dürr, V., Bläsing, B., Schack, T.: Evolutionary optimization of echo state networks: multiple motor pattern learning. Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010. p. 63-71. (2010).
Krause, André Frank, Dürr, Volker, Bläsing, Bettina, and Schack, Thomas. “Evolutionary optimization of echo state networks: multiple motor pattern learning”. Artificial neural networks and intelligent information processing : proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing ; ANNIIP 2010 ; in conjunction with ICINCO 2010, Funchal, Madeira, Portugal, June 2010. 2010. 63-71.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Zuletzt Hochgeladen
2019-09-06T08:48:07Z
MD5 Prüfsumme
025ceff39b03bb9d85e7744d56d59722