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.
Kim, Hyeoncheol and Zobrist, George Winston, "Input Data Pattern Encoding for Neural Net Algorithms" (1990). Computer Science Technical Reports. 68.
© 1990 University of Missouri--Rolla, All rights reserved.