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.
Recommended Citation
Kim, Hyeoncheol and Zobrist, George Winston, "Input Data Pattern Encoding for Neural Net Algorithms" (1990). Computer Science Technical Reports. 68.
https://scholarsmine.mst.edu/comsci_techreports/68
Department(s)
Computer Science
Report Number
CSc-90-3
Document Type
Technical Report
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1990 University of Missouri--Rolla, All rights reserved.
Publication Date
May 1990
Comments
This report is substantially the M.S. thesis of the first author, completed May 1990.