Adaptive Modelling Of Likelihood Classification

Adaptive Modelling of Likelihood Classification

An attempt was made to place the relationship between recognition and classification on the one hand and between theory and application of statistical classification on the other hand, in proper perspective. Compound decision theory is the latest step in the evolution of the most general model in which to imbed statistical classification problems arising in recognition system design. For the nonformalizable aspects of design, interactive approaches, namely those in which the human is part of the loop in the design process, with different classification and heuristic algorithms at his call, seem to be most promising. (Author).

Adaptive Modelling of Likelihood Classification-1

The purpose of this study is the development and evaluation of adaptive networks to represent broad classes of likelihood functions. Orthogonal expansions for multivariate distributions of discrete and continuous random variables are investigated for this application. To overcome the problem of high dimensionality, Markovian processing of discrete spatial patterns is introduced. In addition, adaptive threshold adjustment procedures and an optimal method for taking context into account are derived from Compound Decision Theory. Experimental results, on the classification of visual patterns by a two-layer, two threshold network, are also presented. (Author).

Current Research and Development in Scientific Documentation