Training multilayer neural network based on optimal control theory for limited computational resources

• Main Authors: Alkawaz, Ali Najem, Kanesan, Jeevan, Khairuddin, Anis Salwa Mohd, Badruddin, Irfan Anjum, Kamangar, Sarfaraz, Hussien, Mohamed, Baig, Maughal Ahmed Ali, Ahammad, N. Ameer
• Format: Article
• Published: MDPI 2023
• Subjects: T Technology (General); TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.um.edu.my/38665/
• Institution: Universiti Malaya

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...