On the regularization of convolutional kernel tensors in neural networks

DOI10.1080/03081087.2020.1795058MaRDI QIDQ5095242zbMATH OpenOpenAlexWikidataFDO

Authors Pei-Chang Guo, Qiang Ye

Publication date 5 August 2022

Published in Linear and Multilinear Algebra (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.04866

zbMATH Keywords

convolutional layersgeneralizabilitypenalty functiontransformation matrixunstable gradient

Mathematics Subject Classification ID

Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Artificial intelligence (68Txx)

Recommendations

• Regularization networks with indefinite kernels
• Deep regularization and direct training of the inner layers of neural networks with kernel flows
• Regularization networks and support vector machines
• Kernel analysis of deep networks
• Regularization in kernel learning
• Learning with tensors: a framework based on convex optimization and spectral regularization
• Improved spectral norm regularization for neural networks
• Kernel Based Learning Methods: Regularization Networks and RBF Networks

Cites work

• ARPACK Users' Guide
• Augmented Implicitly Restarted Lanczos Bidiagonalization Methods
• Computing singular values of large matrices with an inverse-free preconditioned Krylov subspace method
• Conjugate Gradient Methods for Toeplitz Systems
• Matrix algorithms. Vol. 2: Eigensystems

Cited in

(2)

• Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network
• On regularization for a convolutional kernel in neural networks

Describes a project that uses

Uses Software

• ARPACK

This page was built for publication: On the regularization of convolutional kernel tensors in neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095242)