Feed-forward neural network for one-to-many mappings using fuzzy sets

Abstract

Feed-forward networks are generally trained to represent functions or many-to-one (m–o) mappings. In this paper, however, a feed-forward network with modified training algorithm is trained to represent multi-valued or one-to-many (o–m) mappings. The o–m mapping is replaced by a m–o mapping with the values corresponding to a value of the independent variable constituting a set. Thus the problem of representing a o–m mapping has been converted into a problem of training a network to return sets rather than vectors. The o–m mapping may have variable multiplicity leading to sets of variable cardinality. The crisp sets of variable cardinality in turn are replaced by fuzzy sets of fixed cardinality by adding elements, called “do not care” which have membership values of zero. Since the target outputs of the feed-forward network are now sets of fixed cardinality and the actual output of a feed-forward network is a vector the training algorithm is modified to take into account the fact that order should be removed as a constraint when the error vector is calculated. Results of simulations show that the method proposed is very effective.