Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations

DOI10.1007/978-3-030-75549-2_3MaRDI QIDQ826129zbMATH OpenOpenAlexFDO

Authors Remco Duits, Jim Portegies, Bart M. N. Smets, E. J. Bekkers

Publication date 20 December 2021

Full work available at URL https://doi.org/10.1007/978-3-030-75549-2_3

zbMATH Keywords

convolutional neural networksPDEsgeometric deep learningmorphological convolutionsscale-space theoryCramér transform

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) PDEs in connection with computer science (35Q68)

Recommendations

• Scale equivariant neural networks with morphological scale-spaces
• Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
• \(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
• Universal approximations of invariant maps by neural networks
• What is... an Equivariant Neural Network?

Cites work

• scientific article; zbMATH DE number 744071 (Why is no real title available?)
• scientific article; zbMATH DE number 2090803 (Why is no real title available?)
• scientific article; zbMATH DE number 845550 (Why is no real title available?)
• scientific article; zbMATH DE number 5681750 (Why is no real title available?)
• Asymptotic expansion of the hypoelliptic heat kernel on the diagonal
• Heat kernel and analysis on manifolds
• Left-invariant parabolic evolutions on \(SE(2)\) and contour enhancement via invertible orientation scores. I: Linear left-invariant diffusion equations on \(SE(2)\)
• Lévy flights: Exact results and asymptotics beyond all orders
• Morphological counterparts of linear shift-invariant scale-spaces
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations
• Optimal paths for variants of the 2D and 3D Reeds-Shepp car with applications in image analysis
• Weighted subcoercive operators on Lie groups

Cited in

(11)

• \(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
• Representation learning on unit ball with 3D roto-translational equivariance
• Scale-covariant and scale-invariant Gaussian derivative networks
• PDE-based group equivariant convolutional neural networks
• Functional properties of PDE-based group equivariant convolutional neural networks
• Analysis of (sub-)Riemannian PDE-G-CNNs
• What is... an Equivariant Neural Network?
• Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
• Scale equivariant neural networks with morphological scale-spaces
• Connections between numerical algorithms for PDEs and neural networks
• Designing rotationally invariant neural networks from PDEs and variational methods

This page was built for publication: Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q826129)