3 papers
cs.LG2026
Parameter-Minimal Neural DE Solvers via Horner Polynomials
T. Matulić, D. Seršić
We propose a parameter-minimal neural architecture for solving differential equations by restricting the hypothesis class to Horner-factorized polynomials, yielding an implicit, di…
cs.LG2024
Subspace Clustering in Wavelet Packets Domain
Ivica Kopriva, Damir Sersic
Subspace clustering (SC) algorithms utilize the union of subspaces model to cluster data points according to the subspaces from which they are drawn. To better address separability…
eess.SP2019
2D PET Image Reconstruction Using Robust L1 Estimation of the Gaussian Mixture Model
Azra Tafro, Damir Seršić, Ana Sović Kržić
An image or volume of interest in positron emission tomography (PET) is reconstructed from pairs of gamma rays emitted from a radioactive substance. Many image reconstruction metho…