scientific article; zbMATH DE number 7049744

zbMath1483.68335arXiv1706.03078MaRDI QIDQ4633035

Alberto Bietti, Julien Mairal

Publication date: 2 May 2019

Full work available at URL: https://arxiv.org/abs/1706.03078

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

stabilitykernel methodsdeep learninginvariant representations

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Information geometry (statistical aspects) (62B11)

Related Items (14)

Relative stability toward diffeomorphisms indicates performance in deep nets* ⋮ Unnamed Item ⋮ Structure preservation for the deep neural network multigrid solver ⋮ Deep learning in random neural fields: numerical experiments via neural tangent kernel ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Stability of the scattering transform for deformations with minimal regularity ⋮ Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods ⋮ Residual networks as flows of diffeomorphisms ⋮ Unnamed Item ⋮ ckn_kernel ⋮ Complete set of translation invariant measurements with Lipschitz bounds ⋮ Convolutional spectral kernel learning with generalization guarantees ⋮ Unnamed Item ⋮ The interpolation phase transition in neural networks: memorization and generalization under lazy training

Uses Software

• Kernel-Machines
• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Invariant kernel functions for pattern analysis and machine learning
• Positive definite functions on spheres
• Group Invariant Scattering
• A Course in Abstract Harmonic Analysis
• 10.1162/15324430260185619
• Theory of Classification: a Survey of Some Recent Advances
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• On invariance and selectivity in representation learning
• Towards a Coherent Statistical Framework for Dense Deformable Template Estimation
• On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions
• Local Geometry of Deformable Templates
• Understanding Machine Learning

This page was built for publication: