Multiple Hyperball CMAC Structure for Large Dimension Mapping

Abstract

The cerebellar model articulation controller (CMAC) is often used in neural computation and neurocontrol systems as output predictors or models of dynamic systems through static mapping from input space to output space. Hyperball CMAC (HCMAC) is presented in the paper. As a fast learning network, its performance is very easy to be analyzed. The simulation results, from the application of three kinds of CMAC, demonstrate that the HCMAC has a better learning performance than CMAC with general basis functions (Chiang; Lin, 1996) and general Albus CMAC (Albus, 1975). For mapping with large-dimensional input, the conventional CMACs need large weight memory space, while the need usually is not met. In order to overcome the issue, a new CMAC structure containing several HCMACs is proposed, the input space of each HCMAC is a subset of input space to be mapped. The CMAC structure is called SHCMAC. Simulations for the SHCMAC used in a multivariable nonlinear dynamic system modelling are performed to demonstrate its powerful associative memory performance and the accuracy in modeling