Some experiments on the use of genetic algorithms in a Boltzmann machine
Bellgard, M.I. and Tsang, C.P. (1991) Some experiments on the use of genetic algorithms in a Boltzmann machine. In: IEEE International Joint Conference of Artificial Neural Networks 1991 (IJCNN '91), 18 - 21 November 1991, Singapore pp. 2645-2652.
*Subscription may be required
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.
|Publication Type:||Conference Paper|
|Item Control Page|
Downloads per month over past year