Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network

Abstract

The important issue for Designing architecture isthe evolution of Artificial Neural Network (ANN). There is no systematic method to design a near-optimal architecture for a given application or task. The pattern classification methods are used to design the neural network architectures and efforts towards the automatic design of network topologies, constructive and destructive algorithms can be used. In the proposed work the optimization of architectures and connection weights uses the evolutionary process. A singlepoint crossover is applied with selective schemas on the network space and evolution is introduced in the mutation stage so that an optimized ANNs are achieved.

AGCS Technique to Improve the Performance of Neural Networks

“…Sagar et al [16] systematically suggested a way to the neural network, which has been measured for adaptive technique that increasingly self-organizes to approximate the solution, creating the situation to solve of the need as well as decidedly specify the actual methods headed for the solution. Moreover, with unnatural neural network, evolutionary computation may very well be included in order to increase the actual performance by various amounts, and consequently this kind of neural network is named as evolutionary ANN.…”