Zobrazeno 1 - 10
of 473
pro vyhledávání: '"HUANG Yujia"'
Autor:
Huang, Yujia, Ghatare, Adishree, Liu, Yuanzhe, Hu, Ziniu, Zhang, Qinsheng, Sastry, Chandramouli S, Gururani, Siddharth, Oore, Sageev, Yue, Yisong
We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord pr
Externí odkaz:
http://arxiv.org/abs/2402.14285
To address the sensitivity of parameters and limited precision for physics-informed extreme learning machines (PIELM) with common activation functions, such as sigmoid, tangent, and Gaussian, in solving high-order partial differential equations (PDEs
Externí odkaz:
http://arxiv.org/abs/2310.13947
Publikováno v:
Magn Reson Med. 2023; 1-10
This study aimed to evaluate the potential of 3D echo-planar imaging (EPI) for improving the reliability of $T_2^*$-weighted ($T_2^*w$) data and quantification of $\textit{R}_2^*$ decay rate and susceptibility ($\chi$) compared to conventional gradie
Externí odkaz:
http://arxiv.org/abs/2308.07811
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under pertu
Externí odkaz:
http://arxiv.org/abs/2210.16940
Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of attack and the classification model, and thus can defend pre-existing c
Externí odkaz:
http://arxiv.org/abs/2205.07460
Publikováno v:
In International Journal of Hydrogen Energy 4 November 2024 89:10-21
Autor:
Wang, Zhiyao, Huang, Yujia, Liu, Xiaoguang, Cao, Wenyan, Ma, Qiang, Qi, Yajie, Wang, Mengmeng, Chen, Xin, Hang, Jing, Tao, Luhang, Yu, Hailong, Li, Yuping
Publikováno v:
In Clinical Neurology and Neurosurgery November 2024 246
Autor:
Liu, Xueqing, Zhang, Xinyu, Ma, Linlin, Qiang, Na, Wang, Jiao, Huang, Yujia, Yuan, Xiaolei, Lu, Chunmei, Cao, Yang, Xu, Jie
Publikováno v:
In Metabolism January 2025 162
Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant. However, such a b
Externí odkaz:
http://arxiv.org/abs/2111.01395
Autor:
Song, Shaoyu, Huang, Yujia, Lian, Jiachang, Cao, Jun, Wang, Jingjing, Zheng, Yingying, Zhu, Mei, Pan, Jiaqi, Li, Chaorong
Publikováno v:
In International Journal of Hydrogen Energy 26 September 2024 84:372-382