The problem of determining the proper size of an artificial neural network is recognized to be crucial, especially for its practical implications in such important issues as learning and generalization, One popular approach tackling this problem is commonly known as pruning and consists of training a larger than necessary network and then removing unnecessary weights/nodes, In this paper, a new pruning method is developed, based on the idea of iteratively eliminating units and adjusting the remaining weights in such a way that the network performance does not worsen over the entire training set, The pruning problem is formulated in terms of solving a system of linear equations, and a very efficient conjugate gradient algorithm is used for solving it, in the least-squares sense, The algorithm also provides a simple criterion for choosing the units to be removed, which has proved to work well in practice. The results obtained over various test problems demonstrate the effectiveness of the proposed approach.

An iterative pruning algoritm for feed-forward neural networks

FANELLI, Anna Maria;CASTELLANO, GIOVANNA;
1997-01-01

Abstract

The problem of determining the proper size of an artificial neural network is recognized to be crucial, especially for its practical implications in such important issues as learning and generalization, One popular approach tackling this problem is commonly known as pruning and consists of training a larger than necessary network and then removing unnecessary weights/nodes, In this paper, a new pruning method is developed, based on the idea of iteratively eliminating units and adjusting the remaining weights in such a way that the network performance does not worsen over the entire training set, The pruning problem is formulated in terms of solving a system of linear equations, and a very efficient conjugate gradient algorithm is used for solving it, in the least-squares sense, The algorithm also provides a simple criterion for choosing the units to be removed, which has proved to work well in practice. The results obtained over various test problems demonstrate the effectiveness of the proposed approach.
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/11586/131212
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 247
  • ???jsp.display-item.citation.isi??? 196
social impact