Prof. Dr. Manish Manoria

University: TRUBA Institute of Engineering & Information Technology, Bhopal (M.P.) India
Department: Department of Computer Science and Engineering
Research Fields: Data Mining, Soft Computing, Information Security, Video & Image Databases


1 Improved Back Propagation Algorithm to Avoid Local Minima in Multiplicative Neuron Model

Authors: Manish Manoria, Kavita Burse, Vishnu P. S. Kirar


The back propagation algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a training algorithm consisting of a learning rate and a momentum factor. The major drawbacks of above learning algorithm are the problems of local minima and slow convergence speeds. The addition of an extra term, called a proportional factor reduces the convergence of the back propagation algorithm. We have applied the three term back propagation to multiplicative neural network learning. The algorithm is tested on XOR and parity problem and compared with the standard back propagation training algorithm.

Keywords: local minima, Three term back propagation, multiplicative neuralnetwork, proportional factor

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2416