Zobrazeno 1 - 10
of 3 753
pro vyhledávání: '"LIAO, HONG"'
Identifying and localizing objects within images is a fundamental challenge, and numerous efforts have been made to enhance model accuracy by experimenting with diverse architectures and refining training strategies. Nevertheless, a prevalent limitat
Externí odkaz:
http://arxiv.org/abs/2410.15346
A unified theoretical framework is suggested to examine the energy dissipation properties at all stages of additive implicit-explicit Runge-Kutta (IERK) methods up to fourth-order accuracy for gradient flow problems. We construct some parameterized I
Externí odkaz:
http://arxiv.org/abs/2410.06463
Publikováno v:
Journal of Computational Physics, 2024, 519: 113456
Explicit integrating factor Runge-Kutta methods are attractive and popular in developing high-order maximum bound principle preserving time-stepping schemes for Allen-Cahn type gradient flows. However, they always suffer from the non-preservation of
Externí odkaz:
http://arxiv.org/abs/2408.14984
Autor:
Wang, Chien-Yao, Liao, Hong-Yuan Mark
This is a comprehensive review of the YOLO series of systems. Different from previous literature surveys, this review article re-examines the characteristics of the YOLO series from the latest technical point of view. At the same time, we also analyz
Externí odkaz:
http://arxiv.org/abs/2408.09332
Autor:
Liao, Hong-lin, Wang, Xuping
Publikováno v:
Mathematics of Computation, 2024
We propose a unified theoretical framework to examine the energy dissipation properties at all stages of explicit exponential Runge-Kutta (EERK) methods for gradient flow problems. The main part of the novel framework is to construct the differential
Externí odkaz:
http://arxiv.org/abs/2404.14893
Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate architecture that can facilitate acquisition of en
Externí odkaz:
http://arxiv.org/abs/2402.13616
We provide a new theoretical framework for the variable-step deferred correction (DC) methods based on the well-known BDF2 formula. By using the discrete orthogonal convolution kernels, some high-order BDF2-DC methods are proven to be stable on arbit
Externí odkaz:
http://arxiv.org/abs/2402.06129
Publikováno v:
Journal of Scientific Computing, 2024, 99:46
We build an asymptotically compatible energy of the variable-step L2-$1_{\sigma}$ scheme for the time-fractional Allen-Cahn model with the Caputo's fractional derivative of order $\alpha\in(0,1)$, under a weak step-ratio constraint $\tau_k/\tau_{k-1}
Externí odkaz:
http://arxiv.org/abs/2311.13216
Multi-task learning (MTL) aims to learn multiple tasks using a single model and jointly improve all of them assuming generalization and shared semantics. Reducing conflicts between tasks during joint learning is difficult and generally requires caref
Externí odkaz:
http://arxiv.org/abs/2309.16921
Publikováno v:
Jichu yixue yu linchuang, Vol 44, Iss 7, Pp 1029-1033 (2024)
Microglial inflammatory response is a pathological process frequently found in patients with depression and in animal models, which is believed to be closely related to depression. The potential mechanisms of inducing microglial inflammatory response
Externí odkaz:
https://doaj.org/article/6c8b985cf6e24db898c1df25f6222512
