Title :
A Least Mean-Squared Error Approach to Syntactic Classification
Author :
Filipski, Alan J.
Author_Institution :
Department of Mathematics, Arizona State University, Tempe, AZ 85281.
fDate :
5/1/1980 12:00:00 AM
Abstract :
The usual approach to numerical training in syntactic pattern recognition involves estimation of the production probabilities of stochastic context-free grammars. Here we describe a different approach, namely that of finding an LMSE discriminant hyperplane between sets of class samples in a space of ``structural indices´´ determined by a context-free grammar.
Keywords :
Additives; Mathematics; Pattern recognition; Production; Stochastic processes; Training data; Discriminant grammars; least mean-squared error; stochastic grammars; structural indices; syntactic pattern recognition;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1980.4767012
