An approach to a consistent qualification of decision procedures in probabilistic information processing

摘要

Pattern recognition seems to be a rather unique field of interwoven logical inference and decision theory applications. The existence of hundreds of theoretical and real pattern recognition devices forms an ideal basis for research on the structures of various approaches and their comparison. The task of pattern recognition is to select a hypotheses out of a set (e.g.: figures 0, …, 9) on the basis of given data (e.g. the black and white points of a digitized picture). There exists an ideal classifier to solve this problem as the theorem of Bayes provides a logically perfect connection between the input data and the result. But as the so called Bayes-machine proves completely unpractical for real purposesit is “approximated” by more or less complex “real” decision procedures.Thus the theorem of Bayes provides a starting point for the application of statistical considerations and information theory to the analysis of the structures of real decision procedures. The results allow a rather consistent and simple comparison of most decision procedures and provide a tool to estimate the performance of a given procedure in a given environment. The results apply not only to pattern recognition but also to many other fields such as imminence analysis and medical diagnosis.