Training Multilayer Neural Network Based on Optimal Control Theory for Limited Computational Resources

Backpropagation (BP)-based gradient descent is the general approach to train a neural network with a multilayer perceptron. However, BP is inherently slow in learning, and it sometimes traps at local minima, mainly due to a constant learning rate. This pre-fixed learning rate regularly leads the BP...

Full description

Bibliographic Details

Published in:	Mathematics
Main Authors:	Ali Najem Alkawaz, Jeevan Kanesan, Anis Salwa Mohd Khairuddin, Irfan Anjum Badruddin, Sarfaraz Kamangar, Mohamed Hussien, Maughal Ahmed Ali Baig, N. Ameer Ahammad
Format:	Article
Language:	English
Published:	MDPI AG 2023-02-01
Subjects:	multilayer neural network optimal control Pontryagin minimum principle backpropagation logic gates
Online Access:	https://www.mdpi.com/2227-7390/11/3/778