An improvement on genetic-based learning method for fuzzy artificial neural networks
Fuzzy artificial neural networks (FANNs), which are the generalizations of artificial neural networks (ANNs), refer to connectionist systems in which all inputs, outputs, weights and biases may be fuzzy values. This paper proposes a two-phase learning method for FANNs, which reduces the generated er...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2009
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/12984/ http://dx.doi.org/10.1016/j.asoc.2009.03.011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Fuzzy artificial neural networks (FANNs), which are the generalizations of artificial neural networks (ANNs), refer to connectionist systems in which all inputs, outputs, weights and biases may be fuzzy values. This paper proposes a two-phase learning method for FANNs, which reduces the generated error based on genetic algorithms (GAs). The optimization process is held on the alpha cuts of each fuzzy weight. Global optimized values of the alpha cuts at zero and one levels are obtained in the first phase and optimal values of several other alpha cuts are obtained in the second phase. Proposed method is shown to be superior in terms of generated error and executed time when compared with basic GA-based algorithms. © 2009 Elsevier B.V. All rights reserved.
|
|---|