5 problems

Let $L_{\mathcal{T}}$ be the ultrametric Laplacian of a finite ultrametric phylogenetic tree, and let its eigenbasis and spectral parameters be used to represent functions on the t…

Let $Z$ be the incidence submanifold of $Y\times X$ defining a double fibration transform, and let $n”$ denote the codimension of the transform. Levelset integral kernels may use a…

Let SEGNN denote the geometric graph neural network used to estimate three-dimensional velocity fields from arterial input meshes, and let $\mathrm{SE}(3)$ denote the group of roto…

The discussion concerns geometric deep learning architectures built as compositions of pooling layers, locally equivariant layers, activation functions, and an output map, for exam…

A classification task is called more complex when it involves greater task complexity, such as the distinction between CIFAR100 and CIFAR10; a Ricci flow assisted Eucl2Hyp2Eucl neu…