A low-dimensional-CMAC-based neural network
Chun-Shin Lin, Chien-Kuo Li · 2002
This paper presents a novel low-dimensional CMAC based neural network. The new neural network requires much smaller memory space than the conventional CMAC and has an excellent learning convergence property compared to well-known multilayer neural networks. Each CMAC in the new structure has a subset of system inputs as its inputs. Several CMACs that have different subsets of inputs form a submodule and many submodules form a neural network. The output of a submodule is the product of its CMACs' outputs. Each submodule implements a self-generated basis function, which is developed during the learning. The outputs from submodules are added up to be the neural network output. Using only a subset of inputs in each CMAC significantly reduces the needed memory space and overcomes the enormous memory size problem in the conventional CMAC in high-dimensional modeling. With the same size of memory, the new structure is able to achieve much smaller learning error compared to the conventional CMAC.