Back to Search
Start Over
An Optimization Methodology for Neural Network Weights and Architectures.
- Source :
-
IEEE Transactions on Neural Networks . Nov2006, Vol. 17 Issue 6, p1452-1459. 8p. 2 Black and White Photographs, 2 Charts. - Publication Year :
- 2006
-
Abstract
- This paper introduces a methodology for neural net- work global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10459227
- Volume :
- 17
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 23177871
- Full Text :
- https://doi.org/10.1109/TNN.2006.881047