Multi-classify Hybrid Multilayered Perceptron (HMLP) Network for Pattern Recognition Applications

Fakroul Ridzuan Bin Hashim,John J Soraghan,Lykourgos Petropoulakis

doi:10.1007/978-3-642-33409-2_3

Fakroul Ridzuan Bin Hashim, John J Soraghan + Show 1 more

Open Access

https://doi.org/10.1007/978-3-642-33409-2_3

Copy DOI

Publication Date: Jan 1, 2012
Citations: 20	License type: cc-by

Affiliation: University of Strathclyde

Abstract

This paper introduces a Hybrid Multilayered Perceptron (HMLP) based classifier known as the Multi-Classify HMLP network (MCHMLP). This network is shown to be able to enhance the performance accuracy when compared to the conventional HMLP network. The Multi-Classify HMLP network architecture is trained using a Modified Recursive Prediction Error (MRPE). This study uses three benchmark datasets in order to measure the capability of the network. The results show that the proposed Multi-Classify HMLP network provides a significant improvement over the conventional HMLP network for pattern recognition applications.

Full Text