Regularising neural networks using flexible multivariate activation function

DOI10.1016/S0893-6080(03)00189-8zbMath1121.68395WikidataQ52000949 ScholiaQ52000949MaRDI QIDQ1877571

Mirko Solazzi, Aurelio Uncini

Publication date: 19 August 2004

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

zbMATH Keywords

Neural networksperceptronSplineMultilayerRegularisationGeneralisationAdaptive activation functionsGeneralised sigmoidal functionsSpline neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

Improving nonlinear modeling capabilities of functional link adaptive filters ⋮ On the theory of flexible neural networks – Part I: a survey paper

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multilayer feedforward networks are universal approximators
• On the Structure of Continuous Functions of Several Variables
• Approximation by superpositions of a sigmoidal function
• Complex discriminative learning Bayesian neural equalizer

This page was built for publication: Regularising neural networks using flexible multivariate activation function