output
20082025
most citedApproximation capability of two hidden layer feedforward neural networks with fixed weights

76 citations

14 papers

cs.DL2025★ 1 cited

Metrics Over Merit: The Hidden Costs of Citation Impact in Research

Vugar Ismailov

Once upon a time, scientists' worth was measured by their ideas, proofs, and perhaps how eloquently they debated Hilbert's problems at seminars. But now, citation metrics have come…

cs.LG2025

On shallow feedforward neural networks with inputs from a topological space

Vugar Ismailov

We study feedforward neural networks with inputs from a topological space (TFNNs). We prove a universal approximation theorem for shallow TFNNs, which demonstrates their capacity t…

cond-mat.str-el2025★ 2 cited

Dynamic scaling and Family-Vicsek universality in quantum spin chains

Cătălin Paşcu Moca, Balázs Dóra, Doru Sticlet +3

The Family-Vicsek scaling is a fundamental framework for understanding surface growth in non-equilibrium classical systems, providing a universal description of temporal surface ro…

cond-mat.str-el2024★ 1 cited

Loss-induced quantum information jet in an infinite temperature Hubbard chain

Patrik Penc, Cătălin Paşcu Moca, Örs Legeza +3

Information propagation in the one-dimensional infinite temperature Hubbard model with a dissipative particle sink at the end of a semi-infinite chain is studied. In the strongly i…

cs.LG2023★ 12 cited

Measure theoretic results for approximation by neural networks with limited weights

Vugar Ismailov, Ekrem Savas

In this paper, we study approximation properties of single hidden layer neural networks with weights varying on finitely many directions and thresholds from an open interval. We ob…

math.AP2022★ 1 cited

Higher order elliptic equations in weighted Banach spaces

Bilal T. Bilalov, Sabina R. Sadigova, Lubomira G. Softova

We consider higher order linear, uniformly elliptic equations with non-smooth coefficients in Banach-Sobolev spaces generated by weighted general Banach Function Space (BFS). Suppo…