2011, Vol.14, No.3, pp.264-268
In this paper we propose a generalized model of
identification which displays flexible transformation within the
framework of generally known paradigms by changing tunings. The
application of this model enables to synthesize various classifiers
using a priori information about definite applied tasks of
identification. So, we describe the approach to the solution of the
problem of generation of representative training sequences and correct
comparative evaluation of classifiers.
Key words:
identification, classifier, neuron model, fuzzy logic
Full text: Acrobat PDF (164KB)
Copyright © Nonlinear Phenomena in Complex Systems. Last updated: November 4, 2011