Logo image
Exploiting layerwise convexity of rectifier networks with sign constrained weights
Journal article   Open access   Peer reviewed

Exploiting layerwise convexity of rectifier networks with sign constrained weights

S. An, F. Boussaid, M. Bennamoun and F. Sohel
Neural Networks, Vol.105, pp.419-430
2018
pdf
layerwise1.pdfDownloadView
Author’s Version Open Access
url
Link to Published Version *Subscription may be requiredView

Abstract

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 the second hidden layer and negative weights in the output layer, are capable of separating any number of disjoint pattern sets. Furthermore, the proposed two-hidden-layer SCRNs can decompose the patterns of each class into several clusters so that each cluster is convexly separable from all the patterns from the other classes. This provides a means to learn the pattern structures and analyse the discriminant factors between different classes of patterns. Experimental results are provided to show the benefits of sign constraints in improving classification performance and the efficiency of the proposed MM algorithm.

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

Source: InCites

Metrics

42 File views/ downloads
131 Record Views

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.17 Computer Vision & Graphics
4.17.128 Deep Visual Recognition
Web Of Science research areas
Computer Science, Artificial Intelligence
Neurosciences
ESI research areas
Computer Science
Logo image