Input data pattern encoding for neural net algorithms

Author

Hyeoncheol Kim

Abstract

"First, a brief overview of neural networks and their applications are described, including the BAM (Bidirectional Associative Memory) model.

A bucket-weight-matrix scheme is proposed, which is a data pattern encoding method that is necessary to transform a set of real-world numbers into neural network state numbers without losing the pattern property the set has. The scheme is designed as a neural net so that it can be combined with other data processing neural nets. The net itself can be used as a bucket-sorting net also. This shows that traditional data structure problems can be an area that neural networks may conquer, too.

A simulation of the net combined with the BAM model on a digital computer is done to show performance of the proposed data encoding method with both non-numerical image pattern and numerical data pattern examples"--Abstract, page iii.

Advisor(s)

Zobrist, George W. (George Winston), 1934-

Committee Member(s)

Prater, John Bruce, 1932-2002
Bourquin, Jack J.

Department(s)

Computer Science

Degree Name

M.S. in Computer Science

Comments

A report which is substantially this thesis is available here for download.

Publisher

University of Missouri--Rolla

Publication Date

Summer 1990

Pagination

ix, 72 pages

Note about bibliography

Includes bibliographical references (page 71).

Rights

© 1990 Hyeoncheol Kim, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Thesis Number

T 6097

Print OCLC #

22895657

Recommended Citation

Kim, Hyeoncheol, "Input data pattern encoding for neural net algorithms" (1990). Masters Theses. 911.
https://scholarsmine.mst.edu/masters_theses/911