Exploiting layerwise convexity of rectifier networks with sign constrained weights

DOI10.1016/j.neunet.2018.06.005zbMath1434.68495arXiv1711.05627OpenAlexW2964187808WikidataQ62789865 ScholiaQ62789865MaRDI QIDQ2181101

Mohammed Bennamoun, Senjian An, Farid Boussaid, Ferdous A. Sohel

Publication date: 18 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.05627

zbMATH Keywords

majorization-minimization algorithmgeometrically interpretable neural networkrectifier neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Multilayer feedforward networks are universal approximators
• Piecewise convexity of artificial neural networks
• Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines
• Deep Belief Networks Are Compact Universal Approximators
• SMC Design for Robust Stabilization of Nonlinear Markovian Jump Singular Systems
• Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
• Majorization-Minimization Algorithms in Signal Processing, Communications, and Machine Learning

This page was built for publication: Exploiting layerwise convexity of rectifier networks with sign constrained weights