Batch Intrinsic Plasticity for Extreme Learning Machines
Neumann K, Steil JJ (2011)
In: Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1. Honkela T, Duch W, Girolami M, Kaski S (Eds); Lecture notes in computer science, 6791. Springer: 339-346.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
NeumannSteil_ICANN2011.pdf
562.71 KB
Autor*in
Herausgeber*in
Honkela, Timo;
Duch, Włodzisław;
Girolami, Mark;
Kaski, Samuel
Einrichtung
Abstract / Bemerkung
Extreme learning machines are single-hidden layer feed- forward neural networks, where the training is restricted to the output weights in order to achieve fast learning with good performance. The success of learning strongly depends on the random parameter initialization. To overcome the problem of unsuited initialization ranges, a novel and efficient pretraining method to adapt extreme learning machines task-specific is presented. The pretraining aims at desired output distributions of the hidden neurons. It leads to better performance and less dependence on the size of the hidden layer.
Stichworte
CoR-Lab Publication
Erscheinungsjahr
2011
Titel des Konferenzbandes
Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1
Serien- oder Zeitschriftentitel
Lecture notes in computer science
Band
6791
Seite(n)
339-346
Konferenz
21st International Conference on Artificial Neural Networks
Konferenzort
Espoo, Finland
Konferenzdatum
2011-06-14 – 2011-06-17
ISBN
978-3-642-21734-0
Page URI
https://pub.uni-bielefeld.de/record/2141968
Zitieren
Neumann K, Steil JJ. Batch Intrinsic Plasticity for Extreme Learning Machines. In: Honkela T, Duch W, Girolami M, Kaski S, eds. Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1. Lecture notes in computer science. Vol 6791. Springer; 2011: 339-346.
Neumann, K., & Steil, J. J. (2011). Batch Intrinsic Plasticity for Extreme Learning Machines. In T. Honkela, W. Duch, M. Girolami, & S. Kaski (Eds.), Lecture notes in computer science: Vol. 6791. Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1 (pp. 339-346). Springer. https://doi.org/10.1007/978-3-642-21735-7_42
Neumann, Klaus, and Steil, Jochen J. 2011. “Batch Intrinsic Plasticity for Extreme Learning Machines”. In Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1, ed. Timo Honkela, Włodzisław Duch, Mark Girolami, and Samuel Kaski, 6791:339-346. Lecture notes in computer science. Springer.
Neumann, K., and Steil, J. J. (2011). “Batch Intrinsic Plasticity for Extreme Learning Machines” in Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1, Honkela, T., Duch, W., Girolami, M., and Kaski, S. eds. Lecture notes in computer science, vol. 6791, (Springer), 339-346.
Neumann, K., & Steil, J.J., 2011. Batch Intrinsic Plasticity for Extreme Learning Machines. In T. Honkela, et al., eds. Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1. Lecture notes in computer science. no.6791 Springer, pp. 339-346.
K. Neumann and J.J. Steil, “Batch Intrinsic Plasticity for Extreme Learning Machines”, Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1, T. Honkela, et al., eds., Lecture notes in computer science, vol. 6791, Springer, 2011, pp.339-346.
Neumann, K., Steil, J.J.: Batch Intrinsic Plasticity for Extreme Learning Machines. In: Honkela, T., Duch, W., Girolami, M., and Kaski, S. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1. Lecture notes in computer science. 6791, p. 339-346. Springer (2011).
Neumann, Klaus, and Steil, Jochen J. “Batch Intrinsic Plasticity for Extreme Learning Machines”. Artificial Neural Networks and Machine Learning – ICANN 2011. Pt. 1. Ed. Timo Honkela, Włodzisław Duch, Mark Girolami, and Samuel Kaski. Springer, 2011.Vol. 6791. Lecture notes in computer science. 339-346.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Name
NeumannSteil_ICANN2011.pdf
562.71 KB
Access Level
Open Access
Zuletzt Hochgeladen
2019-09-06T08:57:32Z
MD5 Prüfsumme
898a5469bffcdc244e96470b90e9ea29
Google Scholar
ISBN Suche