By the same authors

Improving the associative rule chaining architecture

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Full text download(s)

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

Title of host publicationArtificial Neural Networks and Machine Learning - ICANN 2013
DatePublished - 2013
Pages98-105
Number of pages8
PublisherSpringer-Verlag
Place of PublicationBerlin
EditorsV Mladenov, G Palm, B Appollini, P Koprinkova-Hristova, A Villa, N Kasabov
Volume8131 LNCS
Original languageEnglish
ISBN (Electronic)978-3-642-40728-4
ISBN (Print)978-3-642-40727-7

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume8131
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Abstract

This paper describes improvements to the rule chaining architecture presented in [1]. The architecture uses distributed associative memories to allow the system to utilise memory eciently, and superimposed distributed representations in order to reduce the time complexity of a tree search to O(d), where d is the depth of the tree. This new work reduces the memory required by the architecture, and can also further reduce the time complexity.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations