\(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification

DOI10.1007/978-3-030-80209-7_62zbMath1493.68330OpenAlexW3183008213MaRDI QIDQ2117902

Frédéric Barbaresco, Yann Cabanes, Pierre-Yves Lagrave

Publication date: 22 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-80209-7_62

zbMATH Keywords

homogeneous spacesradar clutterhyperbolic embeddingBurg algorithmequivariant neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Harmonic analysis on homogeneous spaces (43A85) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Toeplitz, Cauchy, and related matrices (15B05)

Related Items

\(\mathrm{SL}(2,\mathbb{Z})\)-equivariant machine learning with modular forms theory and applications

Uses Software

• PointConv

Cites Work

• Unnamed Item
• Toeplitz Hermitian positive definite matrix machine learning based on Fisher metric
• A GPU compatible quasi-Monte Carlo integrator interfaced to pySecDec
• Lie Group Convolution Algebras as Deformation Quantizations of Linear Poisson Structures
• Covariant integral quantization of the unit disk