Performance Evaluation of Feed Forward Neural Network for Image Classification

  • Hadaate Ullah Southern University Bangladesh & Dhaka University,Dhaka
  • M.A. Kiber University of Dhaka
  • A.H.M. A. Huq University of Dhaka
  • M.A.S. Bhuiyan Xiamen University Malaysia
Keywords: Activation Function, ANN, Back-Propagation Algorithm, FFNN, Regression

Abstract

Artificial Neural Networks (ANNs) are one of the most comprehensive tools for  classification. In this study, the performance of Feed Forward Neural Network (FFNN) with back-propagation algorithm is used to find out the appropriate activation function in the hidden layer using MATLAB 2013a. Random data has been generated and fetched to FFNN for testing the classification performance of this network. From the values of MSE, response graph and regression coefficients, it is clear that Tan sigmoid activation function is the best choice for the image classification. The FFNN with this activation function is better for any classification purpose of different applications such as aerospace, automotive, materials, manufacturing, petroleum, robotics, communication etc because to perform the classification the network designer  have to choose an activation function.

Author Biography

Hadaate Ullah, Southern University Bangladesh & Dhaka University,Dhaka

Assistant Professor & Head

Electrical & Electronic Engineering

Published
2018-05-19
How to Cite
Ullah, H., Kiber, M., Huq, A. A., & Bhuiyan, M. (2018). Performance Evaluation of Feed Forward Neural Network for Image Classification. Journal of Science and Technology, 10(1). Retrieved from https://publisher.uthm.edu.my/ojs/index.php/JST/article/view/2223