Title :
Hash-coding in CMAC neural networks
Author :
Wang, Zi-Qin ; Schiano, Jeffrey L. ; Ginsberg, Mark
Author_Institution :
Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA
Abstract :
Hash-coding is used in CMAC neural networks to reduce the required memory, thereby making the CMAC practical to implement. In this paper the original motivation and rationale for using hash-coding in CMAC are questioned and it is shown that, contrary to the traditional believe, that hash-coding is unable to enhance CMAC´s approximation ability. A comparison between the CMAC performance obtained with two popular hash-coding methods is given
Keywords :
cerebellar model arithmetic computers; CMAC neural networks; hash-coding; memory requirement; performance evaluation; supervised learning; Hamming distance; Intelligent networks; Least squares approximation; Limit-cycles; Neural networks; Quantization; Supervised learning; Training data;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549156
