mailto:uumlib@uum.edu.my 24x7 Service; AnyTime; AnyWhere

Dynamic training rate for backpropagation learning algorithm

Al-Duais, M. S. and Yaakub, Abdul Razak and Yusoff, Nooraini (2013) Dynamic training rate for backpropagation learning algorithm. In: IEEE 11th Malaysia International Conference on Communications (MICC), 26-28 Nov. 2013, Kuala Lumpur, Malaysia.

[thumbnail of MICC 2013 277-282.pdf] PDF
Restricted to Repository staff only

Download (173kB) | Request a copy

Abstract

In this paper, we created a dynamic function training rate for the Back propagation learning algorithm to avoid the local minimum and to speed up training.The Back propagation with dynamic training rate (BPDR) algorithm uses the sigmoid function.The 2-dimensional XOR problem and iris data were used as benchmarks to test the effects of the dynamic training rate formulated in this paper.The results of these experiments demonstrate that the BPDR algorithm is advantageous with regards to both generalization performance and training speed. The stop training or limited error was determined by1.0 e-5

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Artificial neural networks, Back propagation algorithm, adaptive training, dynamic training rate.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: School of Computing
Depositing User: Prof. Dr. Abd Razak Yaakub
Date Deposited: 10 Nov 2016 03:29
Last Modified: 10 Nov 2016 03:29
URI: https://repo.uum.edu.my/id/eprint/19123

Actions (login required)

View Item View Item