A Generalized Unstructured Artificial Neural Network Architecture: A First Study

Author

Robert S. Woodley, Missouri University of Science and TechnologyFollow
Levent Acar, Missouri University of Science and TechnologyFollow

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.

Recommended Citation

R. S. Woodley and L. Acar, "A Generalized Unstructured Artificial Neural Network Architecture: A First Study," Intelligent Engineering Systems Through Artificial Neural Networks, vol. 11, pp. 601 - 606, American Society of Mechanical Engineers (ASME), Nov 2001.

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

01 Nov 2001