Engineering and Technology - Research article Open Access Logo

BACK PROPAGATION ALGORITHM WITH ADAPTATION LEARNING RATE AND MOMENTUM METHOD IN NEURAL NETWORK CONTROLLER

Tu Diep Cong Thanh 1
Volume & Issue: Vol. 11 No. 3 (2008) | Page No.: 69-78 | DOI: 10.32508/stdj.v11i3.2622
Published: 2008-03-31

Online metrics


Statistics from the website

  • Abstract Views: 2311
  • Galley Views: 1075

Statistics from Dimensions

Copyright The Author(s) 2023. This article is published with open access by Vietnam National University, Ho Chi Minh city, Vietnam. This article is distributed under the terms of the Creative Commons Attribution License (CC-BY 4.0) which permits any use, distribution, and reproduction in any medium, provided the original author(s) and the source are credited. 

Abstract

In recent years, Artificial Neural Network has been successfully used in many industrial applications such as signal processing, image identification, transport, medicine, control… Many neural network control schemes using Back Propagation algorithm have been used for a kind of plant with nonlinearity uncertainties and disturbances. And Gradient Descent is one of popular and simple algorithms for training of neural network. In order to ensure algorithm always converge and fast network training, two methods are used to improve network's performance - Adaptation Learning Rate and Momentum method. In this study, we will simulate, verify and compare those theories using MATLAB package.

Comments