Fully-connected network on noncompact symmetric space and ridgelet transform based on helgason-fourier analysis
Neural network on Riemannian symmetric space such as hyperbolic space and the manifold
of symmetric positive definite (SPD) matrices is an emerging subject of research in …
of symmetric positive definite (SPD) matrices is an emerging subject of research in …
[HTML][HTML] A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks
To investigate neural network parameters, it is easier to study the distribution of parameters
than to study the parameters in each neuron. The ridgelet transform is a pseudo-inverse …
than to study the parameters in each neuron. The ridgelet transform is a pseudo-inverse …
Paley-Wiener theorem for the Joint-Eigenspace Fourier transform on noncompact symmetric spaces
OO Oyadare - arXiv preprint arXiv:2409.09036, 2024 - arxiv.org
This paper conducts a geometric analysis of the Joint-Eigenspace Fourier transform of the
symmetric space of the non-compact type. Our study shows how the Poisson transform …
symmetric space of the non-compact type. Our study shows how the Poisson transform …
Some aspects of Analysis on symmetric spaces and homogeneous trees: from Radon transform to Bergman spaces
M Monti - 2022 - tesidottorato.depositolegale.it
The thesis is focused on the Analysis on two classes of non Euclidean spaces: the
symmetric spaces of the noncompact type and the homogeneous trees. I first solve in both …
symmetric spaces of the noncompact type and the homogeneous trees. I first solve in both …