Conference paper
Some experiments on the use of genetic algorithms in a Boltzmann machine
[Proceedings] 1991 IEEE International Joint Conference on Neural Networks, pp.2645-2652
IEEE International Joint Conference of Artificial Neural Networks 1991 (IJCNN '91) (Singapore, 18/11/1991–21/11/1991)
1991
Abstract
While it appears to be a good idea to use Genetic Algorithm(GA) to train a Neural network, past results do not confirm such optimism. The main problems encountered are the speed of convergence, convergence to the wrong answer, and failure to converge. In this paper we combine GA and Simulated annealing to form a Genetic Boltzmann Machine(GBM) and attempt to understand the properties of such an architecture by experiments. We introduce the concept of weight reordering and demonstrate that it overcomes most of the convergence problems. Results of other experiments are also shown relating to the selection of parameters for the GA the effects of population, different crossover point operators, and hidden units are illustrated. We conclude that with careful design a GBM can perform nearly as well as a Boltzmann Machine in a scalar computer. However, GBM is easily amenable to parallel computation by process farming.
Details
- Title
- Some experiments on the use of genetic algorithms in a Boltzmann machine
- Authors/Creators
- M.I. Bellgard (Author/Creator) - The University of Western AustraliaC.P. Tsang (Author/Creator) - The University of Western Australia
- Publication Details
- [Proceedings] 1991 IEEE International Joint Conference on Neural Networks, pp.2645-2652
- Conference
- IEEE International Joint Conference of Artificial Neural Networks 1991 (IJCNN '91) (Singapore, 18/11/1991–21/11/1991)
- Identifiers
- 991005541671307891
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
197 File views/ downloads
76 Record Views