LAUSR

Considering the non-linear characteristics of the a ctiv tion functions, the entire task is multidimensional and non-linear with a mult imodal target function. Implementing evolutionary computing in the multimodal op timization tasks gives developers new and effective tools for seeking the globa l minimum. A developer has to find the optimal and simple transformation between the realization of a phenotype and a genotype. In the article, a two-layer neural network is analysed. In the first step, the population is created. In the main algori thm loop, a parent selection mechanism is used together with the fitness function. To evaluate the quality of evolutionary computing process different measured characteri stics are used. The final results are depicted using charts and tables.