The binary behavior of activation function in receptive field ofconventional cerebellar model articulation controller (CMAC) affects thecontinuity of the network output. In addition, the original learning scheme ofCMAC may corrupt the previous learning data. A control scheme, whichparallely combines the fuzzy CMAC (FCMAC) and PID, is proposed in thepaper. The weights are updated according to the credits which are assigned to thehypercubers according to their learning histories and fuzzy membership degrees.The FCMAC is powerful in control time-varying processes due to the onlinelearning ability of the FCMAC. Experimental results of temperature control haveshown that the FCMAC with online learning ability can accurately follow thecontrol trajectory and reduce the tracking errors.

Simplified fuzzy ARTMAP(SFAM) is a simplification of fuzzyARTMAP(FAM) in reducing architectural redundancy and computationaloverhead. The performance of individual SFAM depends on the ordering oftraining sample presentation. A multiple classifier combination scheme isproposed in order to overcome the problem. The sum rule voting algorithmcombines the results from several SFAM’s and generates reliable and accuraterecognition conclusion. A confidence vector is assigned to each SFAM. Theconfidence element value can be dynamically adjusted according to the historicalachievements. Experiments of recognizing mechanical workpieces have beenconducted to verify the proposed method. The experimental results have shownthat the fusion approach can achieve reliable recognition.