Title :
The Separating Capacity of a Multithreshold Threshold Element
Author_Institution :
Department of Visual Communication Design, Kyushu Institute of Design, Minami-ku, Fukuoka 815, Japan.
Abstract :
In answer to what represents the intrinsic information-processing capability of the pattern classification system, Cover [1] has defined the separating capacity, and has derived it for the linear machine and the so-called ¿ machine. In this paper, the separating capacity of a multithreshold classification element is obtained. It is shown that the capacity of a multithreshold threshold element with k thresholds-k-threshold element-in n-dimensional space is 2(n + k). A linear machine is a special case in the k-threshold element with k = 1; therefore, its capacity becomes 2(n + 1) from the above result. Further, although it is intuitively apparent that the larger the number of thresholds, the more powerful the information-processing capability of the k-threshold element, using the capacity as a measure of this capability, we may now state that the separating power of the k-threshold element increases linearly with respect to k.
Keywords :
Machine learning; Nearest neighbor searches; Neural networks; Pattern classification; Pattern recognition; Performance evaluation; Piecewise linear techniques; Polarization; Power measurement; Testing; Classifier; learning machine; multithreshold threshold element; parallel hyperplanes; pattern recognition; piecewise linear discriminant function;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1985.4767626