An analysis of numerical issues in neural training by pseudoinversion

DOI10.1007/S40314-015-0246-ZzbMath1405.68278arXiv1508.06092OpenAlexW1950163259MaRDI QIDQ520314

R. Deluca, Rossella Cancelliere, Mario Gai, Luca Rubini, Patrick Gallinari

Publication date: 3 April 2017

Published in: Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1508.06092

zbMATH Keywords

supervised learningregularisationpseudoinverse matrixweights setting

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Uses Software

• UCI-ml

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new Tikhonov regularization method
• Practical complexity control in multilayer perceptrons
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• A Matrix Pseudoinversion Lemma and Its Application to Block-Based Adaptive Blind Deconvolution for MIMO Systems

This page was built for publication: An analysis of numerical issues in neural training by pseudoinversion