Pruning backpropagation neural networks using modern stochastic optimisation techniques |
| |
Authors: | Slawomir W. Stepniewski Prof. Andy J. Keane |
| |
Affiliation: | (1) Department of Electrical Engineering (IETiME), Warsaw University of Technology, Warszawa, Poland;(2) Department of Mechanical Engineering, University of Southampton, SO17 1BJ Highfield, Southampton, UK |
| |
Abstract: | Approaches combining genetic algorithms and neural networks have received a great deal of attention in recent years. As a result, much work has been reported in two major areas of neural network design: training and topology optimisation. This paper focuses on the key issues associated with the problem of pruning a multilayer perceptron using genetic algorithms and simulated annealing. The study presented considers a number of aspects associated with network training that may alter the behaviour of a stochastic topology optimiser. Enhancements are discussed that can improve topology searches. Simulation results for the two mentioned stochastic optimisation methods applied to non-linear system identification are presented and compared with a simple random search. |
| |
Keywords: | Optimisation Neural network Pruning Genetic algorithm Simulated annealing |
本文献已被 SpringerLink 等数据库收录! |