Generalized associative memory models for data fusion
College
College of Computer Studies
Department/Unit
Software Technology
Document Type
Conference Proceeding
Source Title
Proceedings of the International Joint Conference on Neural Networks
Volume
4
First Page
2528
Last Page
2533
Publication Date
9-25-2003
Abstract
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.
html
Recommended Citation
Yap, T. N., & Azcarraga, A. P. (2003). Generalized associative memory models for data fusion. Proceedings of the International Joint Conference on Neural Networks, 4, 2528-2533. Retrieved from https://animorepository.dlsu.edu.ph/faculty_research/542
Disciplines
Computer Sciences
Keywords
Multisensor data fusion; Learning classifier systems; Brain—Mathematical models; Brain—Models
Upload File
wf_no