location: Current position: Home >> Scientific Research >> Paper Publications

111 Convergence of Batch Gradient Method with Penalty and Momentum for GNNM(1,1)

Hits:

Indexed by:会议论文

Date of Publication:2013-01-01

Included Journals:CPCI-S

Page Number:8-12

Abstract:In this paper the penalty term and momentum term are used in batch gradient method which improve the learning method for one-dimensional gray neural network model (GNNM(1,1)). Moreover, the convergence of the modified batch gradient method for GNNM(1,1) is proved.

Pre One:一种实用快速非负矩阵分解算法

Next One:Nonnegative matrix factorization based on linear complementarity problem