White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

An evaluation of standard retrieval algorithms and a binary neural approach

Hodge, V.J. and Austin, J. (orcid.org/0000-0001-5762-8614) (2001) An evaluation of standard retrieval algorithms and a binary neural approach. Neural Networks. pp. 287-303. ISSN 0893-6080

Text (hodgevj9.pdf)

Download (1132Kb)


In this paper we evaluate a selection of data retrieval algorithms for storage efficiency, retrieval speed and partial matching capabilities using a large Information Retrieval dataset. We evaluate standard data structures, for example inverted file lists and hash tables, but also a novel binary neural network that incorporates: single-epoch training, superimposed coding and associative matching in a binary matrix data structure. We identify the strengths and weaknesses of the approaches. From our evaluation, the novel neural network approach is superior with respect to training speed and partial match retrieval time. From the results, we make recommendations for the appropriate usage of the novel neural approach. (C) 2001 Elsevier Science Ltd. All rights reserved.

Item Type: Article
Copyright, Publisher and Additional Information: Copyright © 2001 Elsevier Science B.V. This is an author produced version of a paper published in Neural Networks. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.
Keywords: information retrieval algorithm,binary neural network,correlation matrix memory,word-document association,partial match,storage efficiency,speed of training,speed of retrieval,PARTIAL-MATCH RETRIEVAL
Institution: The University of York
Academic Units: The University of York > Computer Science (York)
Depositing User: Repository Officer
Date Deposited: 13 Dec 2005
Last Modified: 23 May 2016 00:23
Published Version: http://dx.doi.org/10.1016/S0893-6080(00)00097-6
Status: Published
Refereed: Yes
URI: http://eprints.whiterose.ac.uk/id/eprint/883

Actions (repository staff only: login required)