A Theory of Adaptive Pattern Classifiers
- 1 June 1967
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electronic Computers
- Vol. EC-16 (3), 299-307
- https://doi.org/10.1109/pgec.1967.264666
Abstract
This paper describes error-correction adjustment procedures for determining the weight vector of linear pattern classifiers under general pattern distribution. It is mainly aimed at clarifying theoretically the performance of adaptive pattern classifiers. In the case where the loss depends on the distance between a pattern vector and a decision boundary and where the average risk function is unimodal, it is proved that, by the procedures proposed here, the weight vector converges to the optimal one even under nonseparable pattern distributions. The speed and the accuracy of convergence are analyzed, and it is shown that there is an important tradeoff between speed and accuracy of convergence. Dynamical behaviors, when the probability distributions of patterns are changing, are also shown. The theory is generalized and made applicable to the case with general discriminant functions, including piecewise-linear discriminant functions.Keywords
This publication has 6 references indexed in Scilit:
- Pattern Classification by Iteratively Determined Linear and Piecewise Linear Discriminant FunctionsIEEE Transactions on Electronic Computers, 1966
- The use of an adaptive threshold element to design a linear optimal pattern classifierIEEE Transactions on Information Theory, 1966
- Threshold LogicPublished by University of California Press ,1965
- Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern RecognitionIEEE Transactions on Electronic Computers, 1965
- A Mathematical Theory of Pattern RecognitionThe Annals of Mathematical Statistics, 1963
- Linear Decision Functions, with Application to Pattern RecognitionProceedings of the IRE, 1962