AN ARCHITECTURE OF NEURAL NETWORKS WITH INTERVAL WEIGHTS AND ITS APPLICATION TO FUZZY REGRESSION-ANALYSIS

In this paper, we first propose an architecture of neural networks tha t have interval weights and interval biases. A neural network with the proposed architecture maps an input vector of real numbers to an outp ut interval. The target output is also given as an interval. Next we d efine a cost function using the interval output from the neural networ k and the corresponding target output. A learning algorithm is derived from the cost function in a similar manner as the BP (Back-Propagatio n) algorithm. We also show two variations of the learning algorithm fo r the proposed architecture, which lead to the inclusion relation betw een the interval output and the interval target. Last we apply the lea rning algorithms to fuzzy regression analysis where target outputs are given as fuzzy numbers.