Simultaneous Evolution of Architectures and Connection Weights in ANNs

Abstract

Become popular among researchers and practitioners for modelling 
complex real--world problems. One of the latest research areas in 
this field is evolving ANNs. In this paper, we investigate the simultaneous 
evolution of architectures and connection weights in ANNs. In simultaneous 
evolution, we use the concept of multiobjective optimization and subsequently 
evolutionary multiobjective algorithms to evolve ANNs. The results are promising 
when compared with the traditional Backpropagation algorithm.