Abstract
For pattern recognition, the method of approximate reasoning has been realized through backpropagation type neural network. At the learning stage of the neural network, fuzzy linguistic statements have been used. Once learned, any nonfuzzy and/or fuzzy representation of features can be classified. The performance of the proposed recognition scheme has been compared with that of Bayesian classifier and very satisfactory results have been obtained.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call