Zobrazeno 1 - 10
of 519
pro vyhledávání: '"Zhang, Xiyue"'
Model reuse techniques can reduce the resource requirements for training high-performance deep neural networks (DNNs) by leveraging existing models. However, unauthorized reuse and replication of DNNs can lead to copyright infringement and economic l
Externí odkaz:
http://arxiv.org/abs/2407.03883
The ubiquity of deep learning algorithms in various applications has amplified the need for assuring their robustness against small input perturbations such as those occurring in adversarial attacks. Existing complete verification techniques offer pr
Externí odkaz:
http://arxiv.org/abs/2406.10154
Autor:
Venuti, M. B., Zhang, Xiyue S., Lang, Eric J, Addamane, Sadhvikas J., Paik, Hanjong, Allen, Portia, Sharma, Peter, Muller, David, Hattar, Khalid, Lu, Tzu-Ming, Eley, Serena
Skyrmions and antiskyrmions are nanoscale swirling textures of magnetic moments formed by chiral interactions between atomic spins in magnetic non-centrosymmetric materials and multilayer films with broken inversion symmetry. These quasiparticles are
Externí odkaz:
http://arxiv.org/abs/2311.13130
Autor:
Kwiatkowska, Marta, Zhang, Xiyue
Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for deployment in a wide range of applications, such as autonomous systems, medical diagnosis and natural language processing. Early adoption of AI technology for rea
Externí odkaz:
http://arxiv.org/abs/2309.11196
Autor:
Zhou, Wenyi, Bishop, Alexander J., Zhang, Xiyue S., Robinson, Katherine, Lyalin, Igor, Li, Ziling, Bailey-Crandell, Ryan, Cham, Thow Min Jerald, Cheng, Shuyu, Luo, Yunqiu Kelly, Ralph, Daniel C., Muller, David A., Kawakami, Roland K.
Publikováno v:
Phys. Rev. Materials 7, 104004 (2023)
Heterostructures of two-dimensional (2D) van der Waals (vdW) magnets and topological insulators (TI) are of substantial interest as candidate materials for efficient spin-torque switching, quantum anomalous Hall effect, and chiral spin textures. Howe
Externí odkaz:
http://arxiv.org/abs/2308.13620
Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks
Recurrent Neural Networks (RNNs) have achieved tremendous success in processing sequential data, yet understanding and analyzing their behaviours remains a significant challenge. To this end, many efforts have been made to extract finite automata fro
Externí odkaz:
http://arxiv.org/abs/2306.14040
Autor:
Cham, Thow Min Jerald, Dorrian, Reiley J., Zhang, Xiyue S., Dismukes, Avalon H., Chica, Daniel G., May, Andrew F., Roy, Xavier, Muller, David A., Ralph, Daniel C., Luo, Yunqiu Kelly
Magnetic van der Waals heterostructures provide a unique platform to study magnetism and spintronics device concepts in the two-dimensional limit. Here, we report studies of exchange bias from the van der Waals antiferromagnet CrSBr acting on the van
Externí odkaz:
http://arxiv.org/abs/2306.02129
Neural network verification mainly focuses on local robustness properties, which can be checked by bounding the image (set of outputs) of a given input set. However, often it is important to know whether a given property holds globally for the input
Externí odkaz:
http://arxiv.org/abs/2305.03686
While Feedforward Neural Networks (FNNs) have achieved remarkable success in various tasks, they are vulnerable to adversarial examples. Several techniques have been developed to verify the adversarial robustness of FNNs, but most of them focus on ro
Externí odkaz:
http://arxiv.org/abs/2304.10558
Autor:
CHENG Huimin, ZHAO Ge, BAI Li, ZHANG Mingyang, ZHAO Jianmei, ZHANG Qingqing, ZHANG Xiyue, XU Ying, HUANG Xiumei, WANG Lin, LIU Junhui, WANG Junwei
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 36, Iss 3, Pp 246-252 (2024)
ObjectiveTo propose targeted prevention and control measures, improve product quality, and ensure food safety, Salmonella contamination in the production and processing of prefabricated crispy pork in a large food processing factory was analyze
Externí odkaz:
https://doaj.org/article/4c036aa39a194c3080e31a743dcd6e72