Extracting fuzzy if-then rules by using the information matrix technique

摘要: In this paper, we use the information matrix technique to extract fuzzy if?then rules from data including noise. With a normal diffusion function, change all crisp observations of given sample into sets make an matrix. We according centroids rows These are integrated additive system with same rule weight. Such systems can be used as adaptive function approximators. Simulations show that method is very effective compared conventional least-squares and neural network. The best advantage suggested that, it may simplest way data.