Title :
Optimal training of thresholded linear correlation classifiers
Author :
Hildebrandt, Thomas H.
Author_Institution :
Dept. of Electr. & Comput. Eng., North Carolina State Univ., Raleigh, NC, USA
fDate :
11/1/1991 12:00:00 AM
Abstract :
A closed-form solution for improved pattern recognition that reduces the training time to a single epoch (one presentation of each of the training patterns) is presented. It is shown that the corresponding hardware requirements are no greater than those for regular recognition under certain conditions. A simple example which shows that the generalization obtained with the closed-form method exceeds that obtained by a model that admits only diagonal transformations is discussed
Keywords :
correlation methods; learning systems; neural nets; pattern recognition; closed-form method; learning systems; neural nets; optimal training; pattern recognition; thresholded linear correlation classifiers; Closed-form solution; Computer science; Correlators; Hardware; Labeling; Pattern matching; Pattern recognition; Shape;
Journal_Title :
Neural Networks, IEEE Transactions on
