Incorporation of Fuzzy Classification Properties into Backpropagation Learning Algorithm - Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on

Most of the real life classification problems have ill defined, imprecise or fuzzy class boundaries. Feedforward neural networks with conventional backpropagat ion learning algorithm are not tailored to these kinds of classafication problems. Hence, an this paper, feedforward neural networks, that use fuzzy objective functions in the backpropagation learning algorithm, are investigated. A learning algorithm is proposed that minimizes an error term, which takes care of fuzziness in Classification f r o m the point of view of possibilistic approach. Since the proposed algorithm has possibilistic classification ability, it can encompass different backpropagation learning algorithms based on crisp and constrained fuzzy classification. The eficacy of the proposed scheme is demonstrated on a vowel classification problem.