An evaluation of HNeT98 (Holographic Quantum Neural Technology) software package
Loading...
Authors
Langford, Darryl
Subjects
Advisors
Borges, Carlos F.
Date of Issue
2000-06
Date
June 2000
Publisher
Monterey, California. Naval Postgraduate School
Language
en_US
Abstract
This thesis investigates the properties of a software package called HNeT (Holographic/Quantum Neural Technology) which is based on the use of an artificial intelligence tool called Neural Networks. The basis for the investigation of this software is to establish its reliability, effectiveness and efficiency. Neural technology is a technological replication of the biological neural system designed to learn data patterns and process the data (stimulus) and then generate a response based on the memory of the data. HNeT theory is fundamentally different from the standard Artificial Neural System (ANS) in that it uses complex scalars to evaluate internal mappings of one set of values (stimuli) to another set of values (responses). HNeT employs a process known as enfolding, which allows the learning and subsequent recall of many stimulus-response associations to be compressed into a single HNeT neuron cell improving the speed of learning and recall accuracy as well as reducing storage requirements. Whereas the traditional ANS stores stimulus patterns separately as a reference template within a cell and are compared one at a time to a new incoming stimulus response pattern which in this case, requires larger amounts of memory.
Type
Thesis
Description
Series/Report No
Department
Applied Mathematics
Organization
Naval Postgraduate School (U.S.)
Identifiers
NPS Report Number
Sponsors
Funder
Format
xii, 57 p.;28 cm.
Citation
Distribution Statement
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.