Deep neural networks on diffeomorphism groups for optimal shape reparametrization

DOI10.1007/s10543-023-00989-5zbMath1526.65027arXiv2207.11141WikidataQ125560861 ScholiaQ125560861MaRDI QIDQ6093564

Jørgen N. Riseth, Elena Celledoni, Alexander Schmeding, Helge Glöckner

Publication date: 9 October 2023

Published in: BIT (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2207.11141

zbMATH Keywords

shape analysisdiffeomorphism groupdeep learningoptimal reparametrization

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Groups of diffeomorphisms and homeomorphisms as manifolds (58D05) Manifolds of mappings (46T10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Density estimation by dual ascent of the log-likelihood
• Towards a Lie theory of locally convex groups
• Controllability on the group of diffeomorphisms
• Infinite dimensional Lie transformation groups
• The blossoming of Schröder's fourth problem
• Shape analysis on Lie groups and homogeneous spaces
• Diffeomorphism groups of compact convex sets
• Regularity of Lie groups
• Shape analysis of surfaces using general elastic metrics
• Deep learning as optimal control problems: models and numerical methods
• Shape analysis on Lie groups with applications in computer animation
• A proposal on machine learning via dynamical systems
• Constructing reparameterization invariant metrics on spaces of plane curves
• Control on the manifolds of mappings with a view to the deep learning
• Cubic convolution interpolation for digital image processing
• Closed surfaces with different shapes that are indistinguishable by the SRNF
• The inverse function theorem of Nash and Moser
• Stable architectures for deep neural networks
• When unit groups of continuous inverse algebras are regular Lie groups
• Structure-preserving deep learning
• Approximation by superpositions of a sigmoidal function