Accelerated learning for restricted boltzmann machine with a novel momentum algorithm

Xiaoguang Gao, Fei Li, Kaifang Wan

科研成果: 期刊稿件文章同行评审

6 引用 (Scopus)

摘要

We investigated two commonly used momentum algorithms, Classical momentum (CM) and Nesterov momentum (NM). We found that, when used in Restricted Boltzmann machine (RBM), they have two main problems: The first one is their performances are not obvious and not as good as expected. The second one is they may lose accelerating ability in the later stage of training process. Aiming at these two problems, we proposed the Weight momentum algorithm and evaluated our approach on four datasets. It has been demonstrated that our methods can achieve better performance under both reconstruction error and classification rate criterions.

源语言英语
页(从-至)483-487
页数5
期刊Chinese Journal of Electronics
27
3
DOI
出版状态已出版 - 10 5月 2018

指纹

探究 'Accelerated learning for restricted boltzmann machine with a novel momentum algorithm' 的科研主题。它们共同构成独一无二的指纹。

引用此