Zobrazeno 1 - 10
of 1 569
pro vyhledávání: '"Ray, P. C."'
Publikováno v:
Proceedings of the 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), 24-26 July 2024, pp. 135-142
The dramatic surge in the utilisation of generative artificial intelligence (GenAI) underscores the need for a secure and efficient mechanism to responsibly manage, use and disseminate multi-dimensional data generated by artificial intelligence (AI).
Externí odkaz:
http://arxiv.org/abs/2406.11536
Edge computing allows artificial intelligence and machine learning models to be deployed on edge devices, where they can learn from local data and collaborate to form a global model. Federated learning (FL) is a distributed machine learning technique
Externí odkaz:
http://arxiv.org/abs/2405.01189
Autor:
Huang, Junhao, Zhao, Haosong, Zhang, Jipeng, Dai, Wangchen, Zhou, Lu, Cheung, Ray C. C., Koc, Cetin Kaya, Chen, Donglong
This paper presents another improved version of Plantard arithmetic that could speed up Kyber implementations on two low-end 32-bit IoT platforms (ARM Cortex-M3 and RISC-V) without SIMD extensions. Specifically, we further enlarge the input range of
Externí odkaz:
http://arxiv.org/abs/2309.00440
Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and simplificat
Externí odkaz:
http://arxiv.org/abs/2308.02413
Video-based human pose transfer is a video-to-video generation task that animates a plain source human image based on a series of target human poses. Considering the difficulties in transferring highly structural patterns on the garments and disconti
Externí odkaz:
http://arxiv.org/abs/2307.07754
Autor:
Xin, Yao, Tang, Guoming, Chen, Donglong, Zhang, Rumin, Liang, Teng, Cheung, Ray C. C., Koc, Cetin Kaya
Detecting and extracting textual information from natural scene images needs Scene Text Detection (STD) algorithms. Fully Convolutional Neural Networks (FCNs) are usually utilized as the backbone model to extract features in these instance segmentati
Externí odkaz:
http://arxiv.org/abs/2306.11351
Autor:
Dunn, W., Berland, G., Roussos, E., Clark, G., Kollmann, P., Turner, D., Feldman, C., Stallard, T., Branduardi-Raymont, G., Woodfield, E. E., Rae, I. J., Ray, L. C., Carter, J. A., Lindsay, S. T., Yao, Z., Marshall, R., A., A. N. Jaynes, Ezoe, Y., Numazawa, M., Hospodarsky, G. B., Wu, X., Weigt, D. M., Jackman, C. M., Mori, K., Nénon, Q., Desai, R. T, Blum, L. W., Nordheim, T. A., Ness, J. U., Bodewits, D., Kimura, T., Li, W., Smith, H. T., Millas, D., Wibisono, A. D., Achilleos, N., Koutroumpa, D., McEntee, S. C., Collier, H., Bhardwaj, A., Martindale, A., Wolk, S. J., Badman, S. V., Kraft, R. P.
Jupiter's magnetosphere is considered to be the most powerful particle accelerator in the Solar System, accelerating electrons from eV to 70 MeV and ions to GeV energies. How electromagnetic processes drive energy and particle flows, producing and re
Externí odkaz:
http://arxiv.org/abs/2303.02161
Autor:
McKay, Gregory N., Oommen, Anisha, Pacheco, Carolina, Chen, Mason T., Ray, Stuart C., Vidal, René, Haeffele, Benjamin D., Durr, Nicholas J.
Urinary tract infections (UTIs) are a common condition that can lead to serious complications including kidney injury, altered mental status, sepsis, and death. Laboratory tests such as urinalysis and urine culture are the mainstays of UTI diagnosis,
Externí odkaz:
http://arxiv.org/abs/2203.09999
Autor:
Junhao Huang, Alexandre Adomnicăi, Jipeng Zhang, Wangchen Dai, Yao Liu, Ray C. C. Cheung, Çetin Kaya Koç, Donglong Chen
Publikováno v:
Transactions on Cryptographic Hardware and Embedded Systems, Vol 2024, Iss 2 (2024)
Keccak is widely used in lattice-based cryptography (LBC) and its impact to the overall running time in LBC scheme can be predominant on platforms lacking dedicated SHA-3 instructions. This holds true on embedded devices for Kyber and Dilithium, two
Externí odkaz:
https://doaj.org/article/5e78fc90c44a4a0ea9d9e6a83c4bc3c9
Autor:
Liu, Shuo, Wang, Qiaoling, Zhang, Junyi, Lin, Qinliang, Liu, Yao, Xu, Meng, Chueng, Ray C. C., He, Jianfei
We present NetReduce, a novel RDMA-compatible in-network reduction architecture to accelerate distributed DNN training. Compared to existing designs, NetReduce maintains a reliable connection between end-hosts in the Ethernet and does not terminate t
Externí odkaz:
http://arxiv.org/abs/2009.09736