IEEE International Conference on Neural Networks - Conference Proceedings
ページ
1896 - 1900
発行年
1997-06-01
ISSN
1098-7576
出版者
IEEE(Institute of Electrical and Electronics Engineers)
抄録
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.
The effects of quantization on the backpropagation learning
TE-PR-NAKAYAMA-K-1896.pdf
(400.27KB)
