‘Quantum’ Parallel computation with neural networks

Nathan John Burles

‘Quantum’ Parallel computation with neural networks

Computer Science

Research output: Thesis › Master's Thesis

Abstract

Correlation matrix memories have been successfully applied to many domains. This work implements a production system put forward in [Austin, 2003], to demonstrate its viability as an efficient rule-chaining process. Background information on rule-chaining and CMMs is given, followed by a review of the proposed production system.

Throughout the iterative development process, experimentation is performed in order to investigate the effects of changing the properties of vectors used in this system. The results show that generating vectors using the algorithm proposed in [Baum, 1988] with a weight close to log2 of the vector length provides the highest storage capacity.

The simple system implemented in this work performs rule-chaining effectively. This leads to the conclusion that the proposed production system is viable, and that this area warrants further work.

Original language	English
Qualification	Master of Science
Awarding Institution	Computer Science
Supervisors/Advisors	Austin, Jim, Supervisor
Publication status	Published - 2010

Access to Document

quantum-parallel-computation-with-neural-networksAccepted author manuscript, 1.81 MB

Cite this

@mastersthesis{5ab7ef91399e4f118811c188d428ef06,

title = "{\textquoteleft}Quantum{\textquoteright} Parallel computation with neural networks",

abstract = "Correlation matrix memories have been successfully applied to many domains. This work implements a production system put forward in [Austin, 2003], to demonstrate its viability as an efficient rule-chaining process. Background information on rule-chaining and CMMs is given, followed by a review of the proposed production system.Throughout the iterative development process, experimentation is performed in order to investigate the effects of changing the properties of vectors used in this system. The results show that generating vectors using the algorithm proposed in [Baum, 1988] with a weight close to log2 of the vector length provides the highest storage capacity.The simple system implemented in this work performs rule-chaining effectively. This leads to the conclusion that the proposed production system is viable, and that this area warrants further work.",

author = "Burles, {Nathan John}",

year = "2010",

language = "English",

school = "Computer Science",

}

TY - THES

T1 - ‘Quantum’ Parallel computation with neural networks

AU - Burles, Nathan John

PY - 2010

Y1 - 2010

N2 - Correlation matrix memories have been successfully applied to many domains. This work implements a production system put forward in [Austin, 2003], to demonstrate its viability as an efficient rule-chaining process. Background information on rule-chaining and CMMs is given, followed by a review of the proposed production system.Throughout the iterative development process, experimentation is performed in order to investigate the effects of changing the properties of vectors used in this system. The results show that generating vectors using the algorithm proposed in [Baum, 1988] with a weight close to log2 of the vector length provides the highest storage capacity.The simple system implemented in this work performs rule-chaining effectively. This leads to the conclusion that the proposed production system is viable, and that this area warrants further work.

AB - Correlation matrix memories have been successfully applied to many domains. This work implements a production system put forward in [Austin, 2003], to demonstrate its viability as an efficient rule-chaining process. Background information on rule-chaining and CMMs is given, followed by a review of the proposed production system.Throughout the iterative development process, experimentation is performed in order to investigate the effects of changing the properties of vectors used in this system. The results show that generating vectors using the algorithm proposed in [Baum, 1988] with a weight close to log2 of the vector length provides the highest storage capacity.The simple system implemented in this work performs rule-chaining effectively. This leads to the conclusion that the proposed production system is viable, and that this area warrants further work.

M3 - Master's Thesis

ER -