In this work the authors implement in a Multi-Layer Perceptron (MLP) environment a new class of quasi-newtonian (QN) methods. The algorithms proposed in the present paper use in the iterative scheme of a generalized BFGS-method a family of matrix algebras, recently introduced for displacement decompositions and for optimal preconditioning. This novel approach allows to construct methods having an O(n log_2 n) complexity. Numerical experiences compared with the performances of the best QN-algorithms known in the literature confirm the effectiveness of these new optimization techniques.
Di Fiore, C., Fanelli, S., & Zellini, P. (1999). Matrix algebras in quasi-newtonian algorithms for optimal learning in multi-layer perceptrons. In Proceedings of ICONIP 1999 (pp.27-32). N. Kasabov; K. Ko.
Autori: | |
Autori: | Di Fiore, C; Fanelli, S; Zellini, P |
Titolo: | Matrix algebras in quasi-newtonian algorithms for optimal learning in multi-layer perceptrons |
Nome del convegno: | International Conference on Neural Information Processing |
Luogo del convegno: | Dunedin, New Zealand |
Anno del convegno: | 1999 |
Rilevanza: | Rilevanza internazionale |
Sezione: | contributo |
Data di pubblicazione: | 1999 |
Settore Scientifico Disciplinare: | Settore MAT/08 - Analisi Numerica |
Lingua: | English |
Tipologia: | Intervento a convegno |
Citazione: | Di Fiore, C., Fanelli, S., & Zellini, P. (1999). Matrix algebras in quasi-newtonian algorithms for optimal learning in multi-layer perceptrons. In Proceedings of ICONIP 1999 (pp.27-32). N. Kasabov; K. Ko. |
Appare nelle tipologie: | 02 - Intervento a convegno |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
ART.pdf | N/A | Open Access Visualizza/Apri |