Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization
- 1 November 1997
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 17 (3-4) , 167-194
- https://doi.org/10.1016/s0925-2312(97)00050-7
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- Feed-forward neural networksIEEE Potentials, 1994
- Progress in supervised neural networksIEEE Signal Processing Magazine, 1993
- Back-propagation algorithm which varies the number of hidden unitsNeural Networks, 1991
- The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural NetworksNeural Computation, 1990
- A simple procedure for pruning back-propagation trained neural networksIEEE Transactions on Neural Networks, 1990
- Generalizing Smoothness Constraints from Discrete SamplesNeural Computation, 1990
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- What Size Net Gives Valid Generalization?Neural Computation, 1989
- Dynamic Node Creation in Backpropagation NetworksConnection Science, 1989
- Optimization of Control Parameters for Genetic AlgorithmsIEEE Transactions on Systems, Man, and Cybernetics, 1986