Title :
A CMAC-type neural memory for control applications
Author_Institution :
Fachgebiet Regelsystemtheorie und Robotik, Tech. Hochschule Darmstadt, Germany
Abstract :
CMAC is one of the first neural networks successfully applied to real world control problems. Its ability to locally “generalize” an input/output behaviour based on a non-linear input point processing and a linear algorithm for modifying internal states provides fast convergence to an implicit model. In this paper CMAC is shown in its basic functionality. Guidelines for a CMAC hardware realization are discussed, as they were used for the implementation of an ASIC, which now is available in a first version
Keywords :
application specific integrated circuits; cerebellar model arithmetic computers; content-addressable storage; convergence; integrated memory circuits; neural chips; neurocontrollers; ASIC; CMAC hardware realization; CMAC-type neural memory; cerebellar model articulation controller; control applications; fast convergence; implicit model; input/output behaviour; linear algorithm; nonlinear input point processing; Brain modeling; Convergence; Feedforward neural networks; Guidelines; Hardware; Integrated circuit modeling; Mathematical model; Neural networks; Process control; Robots;
Conference_Titel :
Microelectronics for Neural Networks, 1996., Proceedings of Fifth International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-8186-7373-7
DOI :
10.1109/MNNFS.1996.493787
