Population-based Learning Algorithm to Solving Artificial Neural Network Problems

In this paper, an application of the Population-based learning algorithm(PBLA) to Artificial Neural Network(ANN) training is investigated. PBLA has been inspired by analogies to a social phenomenon rather than to evolutionary processes. Whereas evolutionary algorithms emulate basic features of natural evolution including natural selection, hereditary variations, the survival of the fittest, and production of far more offspring than are necessary to replace current generation. The idea of applying various implementations of the Population-based learning algorithm to ANN training has been suggested. Several implementations of the PBLA have been proposed and applied to solving variety of benchmark problems. Initial results were promising showing a good performance of the PBLA as a tool for ANN training.