On the approximation capability of recurrent neural networks
Hammer B (2000)
Neurocomputing 31(1-4): 107-123.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Einrichtung
Abstract / Bemerkung
The capability of recurrent neural networks of approximating functions from lists of real vectors to a real vector space is examined. Any measurable function can be approximated in probability. Additionally, bounds on the resources sufficient for an approximation can be derived in interesting cases. On the contrary, there exist computable mappings on symbolic data which cannot be approximated in the maximum norm. For restricted input length, some continuous functions on real-valued sequences need a number of neurons increasing at least linearly in the input length. On unary sequences, any mapping with bounded range can be approximated in the maximum norm. Consequently, standard sigmoidal networks can compute any mapping on offline inputs as a computational model.
Erscheinungsjahr
2000
Zeitschriftentitel
Neurocomputing
Band
31
Ausgabe
1-4
Seite(n)
107-123
ISSN
09252312
Page URI
https://pub.uni-bielefeld.de/record/2982131
Zitieren
Hammer B. On the approximation capability of recurrent neural networks. Neurocomputing. 2000;31(1-4):107-123.
Hammer, B. (2000). On the approximation capability of recurrent neural networks. Neurocomputing, 31(1-4), 107-123. https://doi.org/10.1016/S0925-2312(99)00174-5
Hammer, Barbara. 2000. “On the approximation capability of recurrent neural networks”. Neurocomputing 31 (1-4): 107-123.
Hammer, B. (2000). On the approximation capability of recurrent neural networks. Neurocomputing 31, 107-123.
Hammer, B., 2000. On the approximation capability of recurrent neural networks. Neurocomputing, 31(1-4), p 107-123.
B. Hammer, “On the approximation capability of recurrent neural networks”, Neurocomputing, vol. 31, 2000, pp. 107-123.
Hammer, B.: On the approximation capability of recurrent neural networks. Neurocomputing. 31, 107-123 (2000).
Hammer, Barbara. “On the approximation capability of recurrent neural networks”. Neurocomputing 31.1-4 (2000): 107-123.
Google Scholar