Second-order networks in Pytorch

DOI10.1007/978-3-030-26980-7_78MaRDI QIDQ2305295zbMATH OpenOpenAlexFDO

Authors Daniel Brooks, Olivier Schwander, Frédéric Barbaresco, Jean-Yves Schneider, Matthieu Cord

Publication date 10 March 2020

Full work available at URL https://doi.org/10.1007/978-3-030-26980-7_78

zbMATH Keywords

covarianceRiemannian machine learningsecond-order neural networkSPD matrix

Mathematics Subject Classification ID

Positive matrices and their generalizations; cones of matrices (15B48) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Positive definite matrices: data representation and applications to computer vision
• Geometry-aware principal component analysis for symmetric positive definite matrices
• Probabilistic learning vector quantization on manifold of symmetric positive definite matrices
• \(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
• Latent sparse representation classification algorithm based on symmetric positive definite manifold

Cited in

(2)

• An adaptively weighted stochastic gradient MCMC algorithm for Monte Carlo simulation and global optimization
• Second-Order Region for Gray–Wyner Network

Describes a project that uses

Uses Software

• PyTorch

This page was built for publication: Second-order networks in Pytorch

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2305295)