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...

Celý popis

Podrobná bibliografia

Vydané v:	Neural networks Ročník 105; s. 419 - 430
Hlavní autori:	An, Senjian, Boussaid, Farid, Bennamoun, Mohammed, Sohel, Ferdous
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Ltd 01.09.2018
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!