USP Electronic Research Repository

Comparison of Back Propagation and Resilient Propagation Algorithm for Spam Classification

Prasad, Navneel and Singh, Rajeshni and Lal, Sunil P. (2013) Comparison of Back Propagation and Resilient Propagation Algorithm for Spam Classification. [Conference Proceedings]

[thumbnail of PID2917751.pdf]
Preview
PDF - Published Version
Download (559kB) | Preview

Abstract

In this paper we compare the performance of back propagation and resilient propagation algorithms in training neural networks for spam classification. Back propagation algorithm is known to have issues such as slow convergence, and stagnation of neural network weights around local optima. Researchers have proposed resilient propagation as an alternative. Resilient propagation and back propagation are very much similar except for the weight update routine. Resilient propagation does not take into account the value of the partial derivative (error gradient), but rather considers only the sign of the error gradient to indicate the direction of the weight update. We show that resilient propagation yields faster convergence and higher accuracy on the UCI Spambase dataset.

Item Type: Conference Proceedings
Additional Information: DOI: 10.1109/CIMSim.2013.14
Uncontrolled Keywords: Neural Networks, Back Propagation, Resilient Propagation, Spam Classification
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Sumeet Lal
Date Deposited: 27 Oct 2015 22:31
Last Modified: 05 Jul 2016 23:49
URI: https://repository.usp.ac.fj/id/eprint/8552

Actions (login required)

View Item View Item