Zobrazeno 1 - 10
of 15 415
pro vyhledávání: '"A. Đorđević"'
Autor:
Farasat, Talaya, Ahmadzai, Atiqullah, George, Aleena Elsa, Qaderi, Sayed Alisina, Dordevic, Dusan, Posegga, Joachim
Software vulnerabilities are a fundamental cause of cyber attacks. Effectively identifying these vulnerabilities is essential for robust cybersecurity, yet it remains a complex and challenging task. In this paper, we present SafePyScript, a machine l
Externí odkaz:
http://arxiv.org/abs/2411.00636
Autor:
Dordevic, Danilo, Kumar, Suryansh
We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic methods into
Externí odkaz:
http://arxiv.org/abs/2409.01082
Autor:
Đorđević, Dušan, Stošić, Marko
The generalized knots-quivers correspondence extends the original knots-quivers correspondence, by allowing higher level generators of quiver generating series. In this paper we explore the underlined combinatorics of such generating series, relation
Externí odkaz:
http://arxiv.org/abs/2408.01832
Autor:
Dordevic, S. V.
Publikováno v:
Physica B 691, 416295 (2024)
Deep learning models were developed and implemented to aid the search for new heavy fermion compounds. For the purpose of these calculations a database of more than 200 heavy fermions was compiled from the literature. The deep learning networks train
Externí odkaz:
http://arxiv.org/abs/2407.17290
Publikováno v:
Tribology in Industry, Vol 40, Iss 4, Pp 692-701 (2018)
A tribological system is a complex non-linear system composed of the elements that are connected structurally and functionally. The aim of this paper is to present an overview of artificial neural networks, its development and applications of neural
Externí odkaz:
https://doaj.org/article/5423075ad9c148888e33714af14d050d
Autor:
Yuan, Samuel, Dordevic, S. V.
Publikováno v:
Scientific Reports 14, 10275 (2024)
Effective computational search holds great potential for aiding the discovery of High-Temperature Superconductors (HTSs), especially given the lack of systematic methods for their discovery. Recent progress has been made in this area with machine lea
Externí odkaz:
http://arxiv.org/abs/2402.00198
Autor:
Đorđević, Dušan, Gočanin, Dragoljub
We provide an account of the issue of Gibbons-Hawking-York-like boundary terms for a gravity theory defined on a Riemman-Cartan spacetime. We further discuss different criteria for introducing boundary terms in some familiar first-order gravity theor
Externí odkaz:
http://arxiv.org/abs/2401.16306
Publikováno v:
Tribology in Industry, Vol 38, Iss 4, Pp 522-529 (2016)
Today highly competitive market and demands for obtain high surface finish and machining of complex shape geometries replace conventional machining processes with non-conventional. Plasma jet cutting is one of these non-conventional processes that pr
Externí odkaz:
https://doaj.org/article/dd4c9328f34e46edb50ac415055ab00f
This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence tasks. We
Externí odkaz:
http://arxiv.org/abs/2311.10642
Publikováno v:
Phys. Rev. D 108, 124008 (2023)
Various attempts to go beyond the theory of General Relativity start from the assumption that spacetime is not a 4-dimensional but rather a higher-dimensional manifold. Among others, braneworld scenarios postulate that the spacetime we effectively ob
Externí odkaz:
http://arxiv.org/abs/2309.03144