Title :
On the training of a multi-resolution CMAC neural network
Author :
Menozzi, Alberico ; Chow, Mo-Yuen
Author_Institution :
Dept. of Electr. & Comput. Eng., North Carolina State Univ., Raleigh, NC, USA
Abstract :
Several artificial neural network architectures have been proposed to solve problems in control systems and system identification. However, not all neural network structures are equally suitable for real-time adaptive situations. Lattice-based Associative Memory Networks (AMNs) have several properties that are attractive for real-time adaptive modeling and control. An example of a lattice-based AMN is the Cerebellar Model Articulation Controller (CMAC) neural network. A hierarchical multi-resolution lattice approach is proposed and investigated through experimentation as a possible approach to alleviate the main drawback of AMNs: the required storage is an exponential function of the number of inputs. Relevant issues are discussed and suggestions for future improvements are given
Keywords :
adaptive control; associative processing; cerebellar model arithmetic computers; identification; learning (artificial intelligence); Cerebellar Model Articulation Controller; artificial neural network architectures; control systems; hierarchical multi-resolution lattice approach; lattice-based Associative Memory Networks; multi-resolution CMAC neural network; neural network training; real-time adaptive modeling; real-time adaptive situations; system identification; Adaptive control; Artificial neural networks; Associative memory; Control systems; Lattices; Neural networks; Programmable control; Shape; System identification; Vectors;
Conference_Titel :
Industrial Electronics, 1997. ISIE '97., Proceedings of the IEEE International Symposium on
Conference_Location :
Guimaraes
Print_ISBN :
0-7803-3936-3
DOI :
10.1109/ISIE.1997.648912
