An Analysis of Migration in the Island Model on Feed Forward Neural Network

Author's Name: Htet Thazin Tike Thein and Khin Mo Mo Tun
Subject Area: Science and Engineering
Subject Computer Science
Section Research Paper

Keyword:

Artificial Neural Network, Differential Evolution Algorithm, Island Model, Migration Topology, Medical Diagnosis


Abstract

In this paper an analysis of migration in island model on feed forward neural network is presented. Feed forward neural network is one of the classification algorithms which, is currently a hot research area in medicine. Constructing a classification model is important in machine learning for a particular task. In this paper, island-based parallel differential evolution algorithm is chosen and applied to feed forward neural network to enhance the learning process and the network learning is validated in terms of convergence rate and classification accuracy. The proposed system implements the island-based training method to be better accuracy and less training time by using and analyzing between four different migration topologies. The proposed method can be used to classify medical datasets with higher accuracy and less training time.

Download Full Paper