Adaptive individual handling for neural network synthesis

Abstract

Neural Network Synthesis is an algorithm capable of creating and learning and artificial neural networks as well as optimizing their structures and connections. The method is based on Analytic Programming and asynchronous implementation of Self-Organising Migration Algorithm. Such approach already recorded several successful application considering practical casers of modelling and simulation. This results vindicate efforts for its further development. This paper explores a possibility to make it more effective by adaptive individual handling. The main idea is an intelligent control the process based on complexity of processed neural network structure. (C) 2016 The Authors. Published by Elsevier Ltd.