Like a dawn light scattering into the cloud sky of A.I., Neural Network and Fuzzy Logic become state-of-the- art technologies in exploring the intellectual. To make a judgment between both technologies, we propose an evaluation on them in the view point of learning to classification. Since there are varieties models proposed within both technologies, we focus on most significant model, i.e., Back Propagation Network (BPN) [1] and Wang's fuzzy rule generator [2]. First in the evaluation, we introduce a Gravity Effect Field to illustrate these two models' influence under the existence of one instance. After that, we virtually construct two classifications problems and discuss the behaviors of both methods through the Gravity Effect Field. Finally, we propose another two real examples to demonstrate the results. We conclude that Wang's more suitable for the piecewise region classification and need representative or complete training samples than BPN. BPN is more training data tolerant and less network parameter sensible than that of Wang's fuzzy rule generator. However, basic instinct problems still exist, BPN behaviors more black box than fuzzy rule generator.
關聯:
Proceedings of the 1996 Asian Fuzzy Systems Symposium--Soft Computing in Intelligent Systems and Information Processing，頁79-84
