A rule chaining architecture using a correlation matrix memory

Authors:
James Austin;Stephen Hobson;Nathan Burles;Simon O'Keefe
Affiliations:
Advanced Computer Architectures Group, Department of Computer Science, University of York, York, UK;Advanced Computer Architectures Group, Department of Computer Science, University of York, York, UK;Advanced Computer Architectures Group, Department of Computer Science, University of York, York, UK;Advanced Computer Architectures Group, Department of Computer Science, University of York, York, UK
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 3
Cited 0

Neural computation and self-organizing maps: an introduction

Neural computation and self-organizing maps: an introduction
Connectionist propositional logic (a simple correlation matrix memory based reasoning system)

Emergent neural computational architectures based on neuroscience
Correlation Matrix Memories

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an architecture based on superimposed distributed representations and distributed associative memories which is capable of performing rule chaining. The use of a distributed representation allows the system to utilise memory efficiently, and the use of superposition reduces the time complexity of a tree search to O(d), where d is the depth of the tree. Our experimental results show that the architecture is capable of rule chaining effectively, but that further investigation is needed to address capacity considerations.