This paper deals with optimal learning and provides a unified viewpoint of most significant results in the field. The focus is on the problem of local minima in the cost function that is likely to affect more or less any learning algorithm. We give some intriguing links between optimal learning and the computational complexity of loading problems. We exhibit a computational model such that the solution of all loading problems giving rise to unimodal error functions require the same time, thus suggesting that they belong to the same computational class.

Bianchini, M., S., F., Gori, M., M., P. (1997). Unimodal Loading Problems. In Mathematics of Neural Networks: Models, Algorithms and Applications (pp. 107-112). BOSTON : KLUWER ACADEMIC PUBLISHERS.

Unimodal Loading Problems

BIANCHINI, MONICA;GORI, MARCO;
1997-01-01

Abstract

This paper deals with optimal learning and provides a unified viewpoint of most significant results in the field. The focus is on the problem of local minima in the cost function that is likely to affect more or less any learning algorithm. We give some intriguing links between optimal learning and the computational complexity of loading problems. We exhibit a computational model such that the solution of all loading problems giving rise to unimodal error functions require the same time, thus suggesting that they belong to the same computational class.
1997
9780792399339
Bianchini, M., S., F., Gori, M., M., P. (1997). Unimodal Loading Problems. In Mathematics of Neural Networks: Models, Algorithms and Applications (pp. 107-112). BOSTON : KLUWER ACADEMIC PUBLISHERS.
File in questo prodotto:
File Dimensione Formato  
Ellacott.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 594.1 kB
Formato Adobe PDF
594.1 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11365/36887
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo