Analysis of deep convolutional networks from group theory viewpoint

MaRDI QIDQ5196302zbMATH OpenFDO

Authors

Publication date 2 October 2019

zbMATH Keywords

deep learningexplaining neural networksgroup theory

Mathematics Subject Classification ID

Symmetric groups (20B30) Artificial neural networks and deep learning (68T07)

Recommendations

• Universality of deep convolutional neural networks
• Group invariance, stability to deformations, and complexity of deep convolutional representations
• Theory of deep convolutional neural networks. II: Spherical analysis
• Theory of deep convolutional neural networks: downsampling
• The Modern Mathematics of Deep Learning

Cited in

(11)

• Lie group impression for deep learning
• Theory of deep convolutional neural networks. II: Spherical analysis
• Mathematical analysis of finite parameter deep neural network models with skip connections from the viewpoint of representation sets
• Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling
• Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
• Understanding image representations by measuring their equivariance and equivalence
• The complexity of explaining neural networks through (group) invariants
• Group invariance, stability to deformations, and complexity of deep convolutional representations
• The complexity of explaining neural networks through (group) invariants
• Analysis on information geometric measurement of internal transfer of deep neural network
• Analysis of (sub-)Riemannian PDE-G-CNNs

This page was built for publication: Analysis of deep convolutional networks from group theory viewpoint

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5196302)