University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Combining multiple modes of information using unsupervised neural classifiers

Ahmad, K, Casey, M, Vrusias, B, Saragiotis, P, Windeatt, T and Roli, F (2003) Combining multiple modes of information using unsupervised neural classifiers In: 4th International Workshop on Multiple Clasifier Systems (MCS 2003), 2003-06-11 - 2003-06-13, UNIV SURREY, GUILDFORD, ENGLAND.

[img]
Preview
PDF
2003_ahmad_casey_vrusias_saragiotis_combining_multiple_modes_of_information.pdf
Available under License : See the attached licence file.

Download (49Kb)
[img] Plain Text (licence)
licence.txt

Download (1516b)

Abstract

A modular neural network-based system is presented where the component networks learn together to classify a set of complex input patterns. Each pattern comprises two vectors: a primary vector and a collateral vector. Examples of such patterns include annotated images and magnitudes with articulated numerical labels. Our modular system is trained using an Unsupervised learning algorithm. One component learns to classify the patterns using the primary vectors and another classifies the same patterns using the collateral vectors. The third combiner network correlates the primary with the collateral. The primary and collateral vectors are mapped on a Kohonen self-organising feature map (SOM), with the combiner based on a variant of Hebbian networks. The classification results appear encouraging,in our attempts to classify 4 set of scene-of-crime images and in our attempts to investigate how pre-school infants relate magnitude to articulated numerical quantities. Certain features of SOM's, namely the topological neighbourhoods of specific nodes, allow for one to many mappings between the primary and collateral maps, hence establishing a broader association between the two vectors when compared with the association due to synchrony in a conventional Hebbian association.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Theory & Methods, Computer Science, FACE RECOGNITION, CLASSIFICATION
Related URLs:
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 17 Jun 2011 16:00
Last Modified: 23 Sep 2013 18:42
URI: http://epubs.surrey.ac.uk/id/eprint/3030

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800