Evolutionary Scanning and Neural Network Optimization

This paper deals with use of an alternative tool for symbolic regression - analytic programming which is able to solve various problems from the symbolic domain as well as genetic programming and grammatical evolution. The main tasks of analytic programming in this paper, is synthesis of a neural network. In this contribution main principles of analytic programming are described and explained. In the second part of the article is in detail described how analytic programming was used for neural network synthesis. An ability to create so called programs, as well as genetic programming or grammatical evolution do, is shown in that part. In this contribution three evolutionary algorithms were used - self organizing migrating algorithm, differential evolution and simulated annealing. The total number of simulations was 150 and results show that the first two used algorithms were more successful than not so robust simulated annealing.