We propose a constructive approach to building single-hidden-layer neural networks for nonlinear function approximation using frequency domain analysis. We introduce a spectrum-based learning procedure that minimizes the difference between the spectrum of the training data and the spectrum of the network's estimates. The network is built up incrementally during training and automatically determines the appropriate number of hidden units. This technique achieves similar or better approximation with faster convergence times than traditional techniques such as backpropagation.

Function approximation : a fast-convergence neural approach based on spectral analysis / C. Citterio, A. Pelagotti, V. Piuri, L. Rocca. - In: IEEE TRANSACTIONS ON NEURAL NETWORKS. - ISSN 1045-9227. - 10:4(1999), pp. 725-740.

Function approximation : a fast-convergence neural approach based on spectral analysis

V. Piuri
Penultimo
;
1999

Abstract

We propose a constructive approach to building single-hidden-layer neural networks for nonlinear function approximation using frequency domain analysis. We introduce a spectrum-based learning procedure that minimizes the difference between the spectrum of the training data and the spectrum of the network's estimates. The network is built up incrementally during training and automatically determines the appropriate number of hidden units. This technique achieves similar or better approximation with faster convergence times than traditional techniques such as backpropagation.
Convergence ; Feedforward neural nets ; Frequency-domain analysis ; Function approximation ; Learning (artificial intelligence) ; Nonlinear functions ; Spectral analysis.
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
1999
Article (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/160332
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 9
social impact