Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Bùi Tuan Anh"'
Autor:
Tran Que Son, Tran Hieu Hoc, Hoang Cong Lam, Tran Manh Hung, Tran Binh Giang, Hoang Manh An, Bùi Tuan Anh, Tran Thu Huong, Nguyen Tien Quyet
Publikováno v:
Asian Journal of Surgery, Vol 46, Iss 2, Pp 780-787 (2023)
Introduction: The goal of this study was to compare the results of LPD with those of open pancreaticoduodenectomy (OPD). Method: Data were retrospectively collected from a database of patients who underwent PD from January 2010 to May 2020. Intraoper
Externí odkaz:
https://doaj.org/article/b6dadc54e1904d86ba64b1676cd3d3d6
This article investigates the torsion homology behaviour in towers of Oeljeklaus-Toma (OT) manifolds. This adapts an idea of Silver and Williams from knot theory to OT-manifolds and extends it to higher degree homology groups.In the case of surfaces,
Externí odkaz:
http://arxiv.org/abs/2406.14942
Despite superior performance in many situations, deep neural networks are often vulnerable to adversarial examples and distribution shifts, limiting model generalization ability in real-world applications. To alleviate these problems, recent approach
Externí odkaz:
http://arxiv.org/abs/2203.00553
Autor:
Bui, Tuan Anh, De Troch, Marleen, Poos, Jan Jaap, Rijnsdorp, Adriaan, Ernande, Bruno, Bekaert, Karen, Mahé, Kélig, Díaz, Kelly, Depestele, Jochen
Publikováno v:
In Estuarine, Coastal and Shelf Science January 2025 312
It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) method, by incorporating adversarial examples during training, re
Externí odkaz:
http://arxiv.org/abs/2202.13437
Publikováno v:
In International Journal of Non-Linear Mechanics June 2024 162
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Composite Structures 1 November 2023 323
We propose two new techniques for training Generative Adversarial Networks (GANs). Our objectives are to alleviate mode collapse in GAN and improve the quality of the generated samples. First, we propose neighbor embedding, a manifold learning-based
Externí odkaz:
http://arxiv.org/abs/1811.01333