Adaptive Fuzzy Inference Neural Network
A =2 • (4) where w/k is the weight between the y'th node in the rule-layer and the Mi node in the output-part. The wjk corresponds to the estimated value of the y'th rule for the Mi node in the output-part. The logical form of the fuzzy inference if-then rules is given such as: If w, is w } / , u2 is w 2 / . . . U j is w^ ...UN} is wNl/- Then yk is wjk . where w;/ means the value near w/- . It should be noted here that it depends on the value of cr;/ .