ABSTRACT
During the last few years there has been a large and energetic upswing in research efforts aimed at synthesizing fuzzy logic with neural networks. This combination of neural networks and fuzzy logic seems natural because the two approaches generally attack the design of “intelligent” systems from quite different angles. Neural networks provide algorithms for learning, classification, and optimization whereas fuzzy logic often deals with issues such as reasoning on a high (semantic or linguistic) level. Consequently the two technologies complement each other [Bez93]. In this paper, we combine neural networks with fuzzy logic techniques. We propose an artificial neural network (ANN) model for a fuzzy logic decision system. The model consists of three layers. The first layer is an input layer. The second layer maps input features to the corresponding fuzzy membership values. The last layer implements the decision rules. The learning process consists of two phases. During the first phase the weights between the last two layers are updated using the gradient descent procedure, and during the second phase the membership functions are updated or tuned. As an illustration the model is used to classify pixels from a multispectral satellite image, a data set representing fruits, and Iris data.
