OCReP: an optimally conditioned regularization for pseudoinversion based neural training

DOI10.1016/j.neunet.2015.07.015zbMath1434.68500arXiv1508.06095OpenAlexW1946718419WikidataQ50567294 ScholiaQ50567294MaRDI QIDQ1669179

Patrick Gallinari, Mario Gai, Luca Rubini, Rossella Cancelliere

Publication date: 30 August 2018

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

Full work available at URL: https://arxiv.org/abs/1508.06095

zbMATH Keywords

condition numbernumerical instabilityregularization parameterpseudoinversion

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (2)

RBF-based partition of unity methods for elliptic PDEs: adaptivity and stability issues via variably scaled kernels ⋮ Distance computation of ontology vector for ontology similarity measuring and ontology mapping

Uses Software

• UCI-ml
• ElemStatLearn
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new Tikhonov regularization method
• Minimax estimation of a multivariate normal mean under arbitrary quadratic loss
• Practical complexity control in multilayer perceptrons
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• A procedure for determination of a good ridge parameter in linear regression
• Distribution-free performance bounds for potential function rules
• Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
• A Monte Carlo Evaluation of Some Ridge-Type Estimators
• Ridge regression iterative estimation of the biasing parameter
• A simulation study of ridge and other regression estimators
• Performance of some new preliminary test ridge regression estimators and their properties
• Choosing Ridge Parameter for Regression Problems
• Tikhonov Regularization and Total Least Squares
• Performance of Some New Ridge Regression Estimators
• 10.1162/153244302760200704
• A Matrix Pseudoinversion Lemma and Its Application to Block-Based Adaptive Blind Deconvolution for MIMO Systems
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• GUEST EDITORS' INTRODUCTION

This page was built for publication: OCReP: an optimally conditioned regularization for pseudoinversion based neural training