Polynomial Representation of Classifiers with Independent Discrete-Valued Features
- 1 February 1972
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. C-21 (2) , 205-208
- https://doi.org/10.1109/tc.1972.5008928
Abstract
It is shown that for n-valued conditionally independent features a large family of classifiers can be expressed as an (n-1)st-degree polynomial discriminant function. The usefulness of the polynomial expansion is discussed and demonstrated by considering the first-order Minkowski metric, the Euclidean distance, and Bayes' classifiers for the ternary-feature case. Finally, some interesting side observations on the classifiers are made with respect to optimality and computational requirements.Keywords
This publication has 11 references indexed in Scilit:
- Algorithms for Recognizing Contour-Traced Handprinted CharactersIEEE Transactions on Computers, 1970
- Linear and quadratic discrimination in pattern recognition (Corresp.)IEEE Transactions on Information Theory, 1969
- Generation of Polynomial Discriminant Functions for Pattern RecognitionIEEE Transactions on Electronic Computers, 1967
- Pattern Classification by Iteratively Determined Linear and Piecewise Linear Discriminant FunctionsIEEE Transactions on Electronic Computers, 1966
- Quadratic discriminant functions in pattern recognition (Corresp.)IEEE Transactions on Information Theory, 1965
- Statistical Independence and Threshold FunctionsIEEE Transactions on Electronic Computers, 1965
- Adaptive Systems in Pattern RecognitionIEEE Transactions on Electronic Computers, 1963
- The hypersphere in pattern recognitionInformation and Control, 1962
- Linear Decision Functions, with Application to Pattern RecognitionProceedings of the IRE, 1962
- Steps toward Artificial IntelligenceProceedings of the IRE, 1961