DHGN network with mode-based receptive fields for 2-dimensional binary pattern recognition

Muhamad Amin, Anang Hudaya (2014) DHGN network with mode-based receptive fields for 2-dimensional binary pattern recognition. In: Hybrid Artificial Intelligence Systems. Lecture Notes in Computer Science (8480). Springer International Publishing, pp. 415-426. ISBN 978-3-319-07616-4

[img] Text
DHGN network with mode-based receptive fields for 2-dimensional binary pattern recognition.pdf
Restricted to Repository staff only

Download (752kB)
Official URL: http://link.springer.com/chapter/10.1007%2F978-3-3...

Abstract

We introduce an extension to existing Distributed Hierarchical Graph Neuron (DHGN) network for 2-dimensional binary pattern recognition. The new form of DHGN network, termed as receptive field DHGN network (RF-DHGN) is a hybrid of a receptive field layer for 2D feature extraction, and one or more DHGN subnets for feature recognition. All inputs to the network, in the form of synaptic weights are automatically determined through mode-based activation function within the RF neurons. The proposed scheme minimizes the need for large number of neurons as compared to the normal DHGN scheme. Furthermore, the results of preliminary recognition tests indicate high recognition accuracy, similar to existing DHGN approach for distributed pattern recognition.

Item Type: Book Section
Additional Information: Book Subtitle: 9th International Conference, HAIS 2014, Salamanca, Spain, June 11-13, 2014. Proceedings
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 21 Jul 2014 07:43
Last Modified: 21 Jul 2014 07:43
URI: http://shdl.mmu.edu.my/id/eprint/5635

Actions (login required)

View Item View Item