Share Email Print

Proceedings Paper

Off-line and on-line backpropagation methods with various levels of redundancy
Author(s): Alessandra Di Medio; Stefano Fanelli; Marco Protasi
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The performance of Back Propagation methods strongly depend on the following two choices: (1) use of off-line or on-line algorithm; (2) level of redundancy of the training set of data. Past investigations studied respectively off-line algorithms with a low degree of redundancy and on- line algorithms with a high degree of redundancy. In this paper we complete the framework considering on-line algorithms with a low level of information and off-line algorithms using training sets with 'redundancy of target data'.

Paper Details

Date Published: 19 August 1993
PDF: 7 pages
Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152630
Show Author Affiliations
Alessandra Di Medio, Univ. of Rome "Tor Vergata" (Italy)
Stefano Fanelli, Univ. of Rome "Tor Vergata" (Italy)
Marco Protasi, Univ. of Rome "Tor Vergata" (Italy)

Published in SPIE Proceedings Vol. 1966:
Science of Artificial Neural Networks II
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top