SU(1,1) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
Deep learning architectures are very efficient in representing complex data. If the problem at hand has symmetries, special architectures are proposed. For instance, convolutional neural networks respect translational symmetry. Group-equivariant neural networks for other group symmetries is a hot topic, and recently they gained huge attention. Recently, for the success of AlphaFold, a system solving the 3D protein structure prediction, group-equivariant neural networks have been instrumental. Group-Convolutional Neural Networks (G-CNN) have been investigated by several authors. The robustness and data effiency of G-CNN are very important in real-world applications. The authors propose an alternative method for building \(\mathrm{SU}(1, 1)\)-equivariant neural networks on the Poincaré disk. In order to obtain good estimates of the integral, they define a Monte-Carlo sampling procedure on \(\mathrm{SU}(1,1)\) by using Helgason-Fourier (HF) transforms of functions defined on homogeneous spaces. As an application they consider classification of Toeplitz-Hermitian positive definite matrices, after a suitable identificiation. This kind of classification can be used in Doppler signal processing tasks. For the entire collection see [Zbl 1482.94007].
- Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
- scientific article; zbMATH DE number 5957433
- Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
- Universal approximations of invariant maps by neural networks
- What is... an Equivariant Neural Network?
- A GPU compatible quasi-Monte Carlo integrator interfaced to pySecDec
- Covariant integral quantization of the unit disk
- scientific article; zbMATH DE number 3864136 (Why is no real title available?)
- Lie Group Convolution Algebras as Deformation Quantizations of Linear Poisson Structures
- Toeplitz Hermitian positive definite matrix machine learning based on Fisher metric
- Iterative SE(3)-transformers
- Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
- Second-order networks in Pytorch
- Equivariant neural networks for inverse problems
- What is... an Equivariant Neural Network?
- Circular-symmetric correlation layer
- Functional properties of PDE-based group equivariant convolutional neural networks
- \(\mathrm{SL}(2,\mathbb{Z})\)-equivariant machine learning with modular forms theory and applications
- Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
This page was built for publication: \(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117902)
