collaborators

5 papers

stat.ML2026

Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks

Roberto Cavoretto, Alessandra De Rossi, Adeeba Haider +1

Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline bases. Although effective, splin…

cs.CE2026

Making Gaussian Kolmogorov-Arnold Networks Reliable and Accurate

Amir Noorizadegan, Sifan Wang, Leevan Ling

Kolmogorov-Arnold Networks (KANs) replace fixed activations with learnable univariate edge functions whose behavior depends strongly on the chosen basis. Gaussian radial basis func…

cs.CV2024

Highway Networks for Improved Surface Reconstruction: The Role of Residuals and Weight Updates

A. Noorizadegan, Y. C. Hon, D. L. Young +1

Surface reconstruction from point clouds is a fundamental challenge in computer graphics and medical imaging. In this paper, we explore the application of advanced neural network a…

cs.AI2024

Stable Weight Updating: A Key to Reliable PDE Solutions Using Deep Learning

A. Noorizadegan, R. Cavoretto, D. L. Young +1

Background: Deep learning techniques, particularly neural networks, have revolutionized computational physics, offering powerful tools for solving complex partial differential equa…

cs.LG2024

Power-Enhanced Residual Network for Function Approximation and Physics-Informed Inverse Problems

Amir Noorizadegan, D. L. Young, Y. C. Hon +1

In this study, we investigate how the updating of weights during forward operation and the computation of gradients during backpropagation impact the optimization process, training…