A proposed max-product threshold unit for classification of pattern vectors

This paper proposes a max-product threshold unit (maptu) that can successfully perform dichotomous classifications of pattern vectors. Maptu, with weight vector, w, classifies a pattern vector, x, by comparing x max-prod w to 0.5. Results obtained by other methods in classification of benchmark data are used for comparison to the method using maptu. The benchmark data consists of the Australian credit data set, cervical cell data set, diabetes data set and the iris data set.