ON THE GRAPHICAL ANALYSIS OF PDF ESTIMATORS FOR PATTERN RECOGNITION

Abstract

The paper demonstrates that graphical methods offer some valuable features in the study of probability density function estimators. The design of experiments to augment our existing knowledge of such estimators is outlined. These experiments use artificial data, which is generated with known characteristics. The use of graphical methods in monitoring PDF performance, during work on real problems, is discussed. There is a brief discussion on the use of graphical displays in an interactive system and the paper concludes with a description of a readily comprehended display of classification results.

Citation

BATCHELOR, B.G. and HAND, D.J. (1975), "ON THE GRAPHICAL ANALYSIS OF PDF ESTIMATORS FOR PATTERN RECOGNITION", Kybernetes, Vol. 4 No. 4, pp. 239-246. https://doi.org/10.1108/eb005400