Improving neural networks generalization with new constructive and pruning methods

Authors:
Marcelo Azevedo Costa;Antônio Pádua Braga;Benjamin Rodrigues de Menezes
Affiliations:
Department of Electronics Engineering, Federal University of Minas Gerais, Campus da UFMG (Pampulha), Caixa Postal 209, CEP 30 161-970, Belo Horizonte, MG, Brazil. E-mail: {mcosta,apbraga,brm}@cpd ...;Department of Electronics Engineering, Federal University of Minas Gerais, Campus da UFMG (Pampulha), Caixa Postal 209, CEP 30 161-970, Belo Horizonte, MG, Brazil. E-mail: {mcosta,apbraga,brm}@cpd ...;Department of Electronics Engineering, Federal University of Minas Gerais, Campus da UFMG (Pampulha), Caixa Postal 209, CEP 30 161-970, Belo Horizonte, MG, Brazil. E-mail: {mcosta,apbraga,brm}@cpd ...
Venue:
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - SBRN'02
Year:
2002

Citing 0
Cited 3

Combination of modified BPNN algorithms and an efficient feature selection method for text categorization

Information Processing and Management: an International Journal
Improving iris recognition through new target vectors in MLP artificial neural networks

ANNPR'12 Proceedings of the 5th INNS IAPR TC 3 GIRPR conference on Artificial Neural Networks in Pattern Recognition
Parallel Training of An Improved Neural Network for Text Categorization

International Journal of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new constructive method and pruning approaches to control the design of Multi-Layer Perceptron (MLP) without loss in performance. The proposed methods use a multi-objective approach to guarantee generalization. The constructive approach searches for an optimal solution according to the pareto set shape with increasing number of hidden nodes. The pruning methods are able to simplify the network topology and to identify linear connections between the inputs and outputs of the neural model. Topology information and validation sets are used.