|
|
|
|
|
Gerasim V. Krivovichev and Valentina Yu. Sergeeva
The paper is devoted to the theoretical and numerical analysis of the two-step method, constructed as a modification of Polyak?s heavy ball method with the inclusion of an additional momentum parameter. For the quadratic case, the convergence conditions ...
ver más
|
|
|
|
|
|
|
|
|
|
|
William Villegas-Ch, Angel Jaramillo-Alcázar and Sergio Luján-Mora
This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Piotr Bortnowski, Robert Król, Natalia Suchorab-Matuszewska, Maksymilian Ozdoba and Mateusz Szczerbakowicz
This study examines the optimization of ore receiving bins in underground copper mines, targeting the reduction of rapid wear and tear on bin components. The investigation identifies the primary wear contributors as the force exerted by the accumulated o...
ver más
|
|
|
|
|
|
|
|
|
|
|
Nikola ?igulic, Matko Glucina, Ivan Lorencin and Dario Matika
This study delves into the vital missions of the armed forces, encompassing the defense of territorial integrity, sovereignty, and support for civil institutions. Commanders grapple with crucial decisions, where accountability underscores the imperative ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Donghyuk Kum, Jichul Ryu, Yongchul Shin, Jihong Jeon, Jeongho Han, Kyoung Jae Lim and Jonggun Kim
This study accounted for the importance of daily expansion flow data in compensating for insufficient flow data in a watershed. In particular, the 8-day interval flow measurement data (intermittent monitoring data) could cause uncertainty in the high- or...
ver más
|
|
|
|
|
|
|
|
|
|
|
Siyuan Xing and Jian-Qiao Sun
The Gaussian-radial-basis function neural network (GRBFNN) has been a popular choice for interpolation and classification. However, it is computationally intensive when the dimension of the input vector is high. To address this issue, we propose a new fe...
ver más
|
|
|
|
|
|
|
|
|
|
|
Lars Radtke, Georgios Bletsos, Niklas Kühl, Tim Suchan, Thomas Rung, Alexander Düster and Kathrin Welker
In the last decade, parameter-free approaches to shape optimization problems have matured to a state where they provide a versatile tool for complex engineering applications. However, sensitivity distributions obtained from shape derivatives in this cont...
ver más
|
|
|
|
|
|
|
|
|
|
|
Peter Marvin Müller, Georgios Bletsos and Thomas Rung
The contribution is devoted to combined shape- and mesh-update strategies for parameter-free (CAD-free) shape optimization methods. Three different strategies to translate the shape sensitivities computed by adjoint shape optimization procedures into sim...
ver más
|
|
|
|
|
|
|
|
|
|
|
Predrag S. Stanimirovic, Bilall I. Shaini, Jamilu Sabi?u, Abdullah Shah, Milena J. Petrovic, Branislav Ivanov, Xinwei Cao, Alena Stupina and Shuai Li
This research proposes and investigates some improvements in gradient descent iterations that can be applied for solving system of nonlinear equations (SNE). In the available literature, such methods are termed improved gradient descent methods. We use v...
ver más
|
|
|
|
|
|
|
|
|
|
|
George Tzougas and Konstantin Kutzkov
We developed a methodology for the neural network boosting of logistic regression aimed at learning an additional model structure from the data. In particular, we constructed two classes of neural network-based models: shallow?dense neural networks with ...
ver más
|
|
|
|
|
|