DocumentCode :
3207742
Title :
Constructive and pruning methods for neural network design
Author :
Costa, Marcelo Azevedo ; Braga, Antonio Pádua ; De Menezes, Benjamin Rodrigues
Author_Institution :
Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
fYear :
2002
fDate :
2002
Firstpage :
49
Lastpage :
54
Abstract :
This paper presents methods to improve generalization of multilayer perceptron (MLP) by pruning the original topology without loss in performance. Topology information and validation sets are used. The results show that these techniques are able to choose a minimum network topology and to simplify trained networks.
Keywords :
generalisation (artificial intelligence); multilayer perceptrons; MLP; constructive methods; generalization; minimum network topology; multilayer perceptron; neural network design; topology information sets; topology pruning; topology validation sets; trained networks; Multilayer perceptrons; Network topology; Neural networks; Performance loss; Sampling methods; Shape; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2002. SBRN 2002. Proceedings. VII Brazilian Symposium on
Print_ISBN :
0-7695-1709-9
Type :
conf
DOI :
10.1109/SBRN.2002.1181434
Filename :
1181434
Link To Document :
بازگشت