In this paper, we present a new class of quasi-Newton methods for the effective learning in large multilayer perceptron (MLP)-networks. The algorithms introduced in this work, named LQN, utilize an iterative scheme of a generalized BFGS-type method, involving a suitable family of matrix algebras L. The main advantages of these innovative methods are based upon the fact that they have an O(n log_2 n) complexity per step and that they require O(n) memory allocations. Numerical experiences, performed on a set of standard benchmarks of MLP-networks, show the competitivity of the LQN methods, especially for large values of n.

Bortoletti, A., DI FIORE, C., Fanelli, S., Zellini, P. (2003). A new class of quasi-newtonian methods for optimal learning in MLP-networks. IEEE TRANSACTIONS ON NEURAL NETWORKS, 14(2), 263-273.

A new class of quasi-newtonian methods for optimal learning in MLP-networks

DI FIORE, CARMINE;FANELLI, STEFANO;ZELLINI, PAOLO
2003-01-01

Abstract

In this paper, we present a new class of quasi-Newton methods for the effective learning in large multilayer perceptron (MLP)-networks. The algorithms introduced in this work, named LQN, utilize an iterative scheme of a generalized BFGS-type method, involving a suitable family of matrix algebras L. The main advantages of these innovative methods are based upon the fact that they have an O(n log_2 n) complexity per step and that they require O(n) memory allocations. Numerical experiences, performed on a set of standard benchmarks of MLP-networks, show the competitivity of the LQN methods, especially for large values of n.
2003
Pubblicato
Rilevanza internazionale
Articolo
Sì, ma tipo non specificato
Settore MAT/08 - ANALISI NUMERICA
English
Con Impact Factor ISI
Fast discrete transforms; neural networks; quasi-Newton methods
Bortoletti, A., DI FIORE, C., Fanelli, S., Zellini, P. (2003). A new class of quasi-newtonian methods for optimal learning in MLP-networks. IEEE TRANSACTIONS ON NEURAL NETWORKS, 14(2), 263-273.
Bortoletti, A; DI FIORE, C; Fanelli, S; Zellini, P
Articolo su rivista
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/2108/14726
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 39
  • ???jsp.display-item.citation.isi??? 33
social impact