Title :
The effects of quantization on the backpropagation learning
Author :
Ikeda, Kazushi ; Suzuki, Akihiro ; Nakayama, Kenji
Author_Institution :
Dept. of Electr. & Comput. Eng., Kanazawa Univ., Japan
Abstract :
The effects of the quantization of the parameters of a learning machine are discussed. The learning coefficient should be as small as possible for a better estimate of parameters. On the other hand, when the parameters are quantized, it should be relatively larger in order to avoid the paralysis of learning originated from the quantization. How to choose the learning coefficient is given in this paper from the statistical point of view
Keywords :
backpropagation; neural nets; quantisation (signal); statistical analysis; backpropagation learning; learning coefficient; parameter estimation; quantization; statistical approach; Backpropagation algorithms; Circuits; Computer errors; Equations; Machine learning; Multilayer perceptrons; Neurons; Parameter estimation; Quantization; Stochastic processes;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614188
