Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon or slower convergence speed due to larger fixed or smaller fixed learning rate respectively. The present research deals with offering two solutions for this problem. The original idea of the present research is using changeable learning rate at each state of training phase in the CMAC model. The first algorithm deals with a new learning rate based on reviation of learning rate. The second algorithm deals with number of training iteration and performance learning, with respect to this fact that error is compatible with inverse training time. Simulation results show that this algorithms have faster convergence and better performance in comparison to conventional CMAC model in all training cycles.

This paper proposes a new solution for controlling complex nonlinear systems, through the combination of a type 2 fuzzy CMAC controller and Jordan neural network. This method takes advantage of type 2 fuzzy CMAC in dealing with uncertainties and learning ability, while the Jordan neural network helps to enhance the stability and improve the performance of the system. The adaptive learning laws were designed to help the proposed network automatically update the network parameters. The results from simulations and experiments have shown that this method achieves superior accuracy and robustness compared to other methods. When applied to control the Magnetic Levitation System, this method shows great potential in solving complex nonlinear control problems, opening up new approaches in this field.

This paper introduces a new structure in neural networks called TD-CMAC, an extension to the conventional Cerebellar Model Arithmetic Computer (CMAC), having reasonable ability in time series prediction. TD-CMAC, the conventional CMAC and a classical neural network model called Multi-Layer Perceptron (MLP) are simulated and evaluated for 1-hour-ahead prediction and 24-hour-ahead prediction of carbon monoxide as one of primary air pollutants. Carbon monoxide data used in this evaluation were recorded and averaged at Villa station in Tehran, Iran from October 3thrd. 2001 to March 14th. 2002 at one-hour intervals. The results show that the errors made by TD-CMAC is fewer than those made by other models.

A control strategy on a hybrid vehicle can be implemented through different methods. In this paper, the Cerebellar Model Articulation Controller (CMAC) and Radial Basis Function (RBF) neural networks were applied to develop an optimal control strategy for a split parallel hydraulic hybrid vehicle. These networks contain a nonlinear mapping, and, also, the fast learning procedure has made them desirable for online control. The RBF network was constructed with the use of the K-mean clustering method, and the CMAC network was investigated for different association factors. Results show that the binary CMAC has better performance over the RBF network. Also, the hybridization of the vehicle results in considerable reduction in fuel consumption.