Generalized associative memory models for data fusion

The Hopfield and bi-directional associative memory (BAM) models are well developed and carefully studied models for associative memory that are patterned after the memory structure of the animal brain. Their basic limitation is that they can only perform associations between at most two sets of patt...

Full description

Saved in:
Bibliographic Details
Main Authors: Yap, Teddy N., Azcarraga, Arnulfo P.
Format: text
Published: Animo Repository 2003
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/faculty_research/542
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
id oai:animorepository.dlsu.edu.ph:faculty_research-1541
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:faculty_research-15412022-01-06T06:04:36Z Generalized associative memory models for data fusion Yap, Teddy N. Azcarraga, Arnulfo P. The Hopfield and bi-directional associative memory (BAM) models are well developed and carefully studied models for associative memory that are patterned after the memory structure of the animal brain. Their basic limitation is that they can only perform associations between at most two sets of patterns. Several different models for generalized associative memory are proposed here. These models are all extensions of the Hopfield and BAM models that can perform multiple associations. Extensive software simulations are conducted to evaluate the different models, using the memory capacity as basis for comparing their performance. The use of the Widrow-Hoff gradient descent error correction algorithm is introduced that can improve the memory capacities of the various models. Potential application of these models as data fusion systems is explored. 2003-09-25T07:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/542 Faculty Research Work Animo Repository Multisensor data fusion Learning classifier systems Brain—Mathematical models Brain—Models Computer Sciences
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
topic Multisensor data fusion
Learning classifier systems
Brain—Mathematical models
Brain—Models
Computer Sciences
spellingShingle Multisensor data fusion
Learning classifier systems
Brain—Mathematical models
Brain—Models
Computer Sciences
Yap, Teddy N.
Azcarraga, Arnulfo P.
Generalized associative memory models for data fusion
description The Hopfield and bi-directional associative memory (BAM) models are well developed and carefully studied models for associative memory that are patterned after the memory structure of the animal brain. Their basic limitation is that they can only perform associations between at most two sets of patterns. Several different models for generalized associative memory are proposed here. These models are all extensions of the Hopfield and BAM models that can perform multiple associations. Extensive software simulations are conducted to evaluate the different models, using the memory capacity as basis for comparing their performance. The use of the Widrow-Hoff gradient descent error correction algorithm is introduced that can improve the memory capacities of the various models. Potential application of these models as data fusion systems is explored.
format text
author Yap, Teddy N.
Azcarraga, Arnulfo P.
author_facet Yap, Teddy N.
Azcarraga, Arnulfo P.
author_sort Yap, Teddy N.
title Generalized associative memory models for data fusion
title_short Generalized associative memory models for data fusion
title_full Generalized associative memory models for data fusion
title_fullStr Generalized associative memory models for data fusion
title_full_unstemmed Generalized associative memory models for data fusion
title_sort generalized associative memory models for data fusion
publisher Animo Repository
publishDate 2003
url https://animorepository.dlsu.edu.ph/faculty_research/542
_version_ 1722366371676815360