Exploiting layerwise convexity of rectifier networks with sign constrained weights

By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization–minimization (MM) algorithms. We prove that the proposed two-hidden-layer SCRNs, which exhibit negative weights in...

Full description

Bibliographic Details

Published in:	Neural networks Vol. 105; pp. 419 - 430
Main Authors:	An, Senjian, Boussaid, Farid, Bennamoun, Mohammed, Sohel, Ferdous
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01.09.2018
Subjects:	Geometrically interpretable neural network Rectifier neural network The majorization–minimization algorithm Geometrically interpretable neural network The majorization–minimization algorithm Rectifier neural network
ISSN:	0893-6080, 1879-2782, 1879-2782
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!