Zobrazeno 1 - 10
of 1 817
pro vyhledávání: '"Wang, AiLi"'
Autor:
Yu, Chengting, Zhang, Fengzhao, Chen, Ruizhe, Liu, Zuozhu, Tan, Shurun, Li, Er-Ping, Wang, Aili
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a well-performed l
Externí odkaz:
http://arxiv.org/abs/2411.01547
Recent insights have revealed that rate-coding is a primary form of information representation captured by surrogate-gradient-based Backpropagation Through Time (BPTT) in training deep Spiking Neural Networks (SNNs). Motivated by these findings, we p
Externí odkaz:
http://arxiv.org/abs/2410.11488
Autor:
Xu, Linqiang, Hu, Yue, Xu, Lianqiang, Xu, Lin, Li, Qiuhui, Wang, Aili, Lau, Chit Siong, Lu, Jing, Ang, Yee Sin
Ultrathin oxide semiconductors with sub-1-nm thickness are promising building blocks for ultrascaled field-effect transistor (FET) applications due to their resilience against short-channel effects, high air stability, and potential for low-energy de
Externí odkaz:
http://arxiv.org/abs/2409.08096
Spiking neural networks (SNNs) have low power consumption and bio-interpretable characteristics, and are considered to have tremendous potential for energy-efficient computing. However, the exploration of SNNs on image generation tasks remains very l
Externí odkaz:
http://arxiv.org/abs/2402.11588
Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restricted model parallelization. As an alternative, greedy local learning pa
Externí odkaz:
http://arxiv.org/abs/2312.07636
Autor:
Xu, Linqiang, Xu, Lianqiang, Lan, Jun, Li, Yida, Li, Qiuhui, Wang, Aili, Guo, Ying, Ang, Yee Sin, Quhe, Ruge, Lu, Jing
Ultra-thin (UT) oxide semiconductors are promising candidates for back-end-of-line (BEOL) compatible transistors and monolithic three-dimensional integration. Experimentally, UT indium oxide (In$_2$O$_3$) field-effect transistors (FETs) with thicknes
Externí odkaz:
http://arxiv.org/abs/2311.02943
Autor:
Xu, Linqiang, Xu, Lianqiang, Li, Qiuhui, Fang, Shibo, Li, Ying, Guo, Ying, Wang, Aili, Quhe, Ruge, Ang, Yee Sin, Lu, Jing
Gate-all-around (GAA) nanowire (NW) field-effect transistor (FET) is a promising device architecture due to its superior gate controllability than that of the conventional FinFET architecture. The significantly higher electron mobility of indium phos
Externí odkaz:
http://arxiv.org/abs/2308.14045
Autor:
Wang, Aili
Iron is one of the most common trace elements in natural water sources and an important component to living systems. The existence of iron may not only cause metallic flavor, it may also deeply impact health of human and animals by interacting with c
Externí odkaz:
http://hdl.handle.net/10919/78796
Publikováno v:
Frontiers in neuroscience, 2022, 12
Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological plausibility. T
Externí odkaz:
http://arxiv.org/abs/2210.05241
Publikováno v:
Zhongliu Fangzhi Yanjiu, Vol 51, Iss 4, Pp 259-264 (2024)
Objective To explore the therapeutic effect of "jian pi yi qi yang xue zhi tong" for treating bone metastasis of breast cancer and the clinical effect of improving pain symptoms. Methods A total of 80 patients with bone metastases from breast cancer
Externí odkaz:
https://doaj.org/article/5484822e356048e882d535eadb6f166b
