A Neuro-Fuzzy Classifier and Its Applications

membership in each class. This viewpoint not only reflects the reality of many applications in which categories have fuzzy boundaries, but also Provides a simple representstion of the potentially complex partition of the feature space. In brief, we use fuzzy i fthen rules to describe a ChsSifier. A typical fuzzy classification rule is like: Fuzzy classification is the task of partitioning a feature space into fuzzy classes. A learn-by-example mechanism is desirable to automate the construction process of a fuzzy classifier. In this paper we introduce a method of employing adaptive networks to solve a fuzzy classification problem. System parameters, such as the membership if XI is A and X2 is B then Z is C, functions defined for each feature and the parameterized t-norms used to combine conjunctive conditions are calibrated with backpropagation. To explain this new approach, first we introduce the concept of adaptive networks and derive a supervised learning procedure based on a gradient descent algorithm to update the parameters in an adaptive network. Next, we apply the proposed architecture to two problems: twospiral classification and Iris categorization. From the experiment results, it is summarized that the adaptively adjusted classifier performs well on an Iris classification problem. The results are discussed from the viewpoint of feature selection.