Article
A Generalized Unstructured Artificial Neural Network Architecture: A First Study
Intelligent Engineering Systems Through Artificial Neural Networks
Abstract
In this document, we will present an unstructured neural network based on the mathematics of holographic storage. We analyzed the mathematics to produce a general mathematical description of the holographic process. From this analysis we are able to show how the holographic process can be used as an associative memory network. Additionally, the process may also be used as a regular feed-forward network. The most striking aspect of these networks is that using the holographic process, they are trained in a single iteration, and may be updated in real time.
Meeting Name
Artificial Neural Networks in Engineering Conference, ANNIE 2001 (2001: Nov. 4-7, St. Louis, MO)
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
- Associative Memory Network,
- Neural Networks,
- Unstructured Neural Network
International Standard Book Number (ISBN)
0-7918-0176-4
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2001 American Society of Mechanical Engineers (ASME), All rights reserved.
Publication Date
11-1-2001
Publication Date
01 Nov 2001
Disciplines
Citation Information
Robert S. Woodley and Levent Acar. "A Generalized Unstructured Artificial Neural Network Architecture: A First Study" Intelligent Engineering Systems Through Artificial Neural Networks Vol. 11 (2001) p. 601 - 606 Available at: http://works.bepress.com/levent-acar/13/