Fuzzification of input vectors for improving the generalization ability of neural networks

Abstract

We propose an approach for improving the generalization ability of multilayer feedforward neural networks. Our approach is based on the fuzzification of input vectors. In our approach, a neural network is trained by fuzzy input vectors. The aim of such fuzzification in the learning phase is to avoid the overfitting of the neural network. In the classification phase, each new pattern is fuzzified, and the fuzzy input vector is presented to the trained neural network. The classification of each new pattern is performed based on the corresponding fuzzy output vector from the trained neural network. The aim of the fuzzification in the classification phase is to reject the classification of new patterns close to the classification boundary. The introduction of a reject option can decrease the misclassification rate on new patterns. We examine the effectiveness of our approach by computer simulations on real-world pattern classification problems.