Title :
A new neural network structure composed of small CMACs
Author :
Lin, Chun-shin ; Li, Chien-Kuo
Author_Institution :
Missouri Univ., Columbia, MO, USA
Abstract :
A new neural network structure that consists of several small CMACs is proposed. The structure is a memory based neural network. While the memory cost has been reduced and the memory technology has improved in the past decade, practical implementation of the proposed structure is inexpensive. The new structure overcomes the huge memory size problem, which exists in the conventional CMAC in high-dimensional modeling. The new neural network will be able to better utilize the memory in learning all kinds of mapping
Keywords :
cerebellar model arithmetic computers; neural net architecture; cerebellar model articulation controller; mapping; memory based neural network; neural network structure; small CMACs; Control systems; Convergence; Input variables; Lakes; Multi-layer neural network; Neural networks; Radial basis function networks; Random access memory; Read-write memory; System identification;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549170
