Zobrazeno 1 - 10
of 444
pro vyhledávání: '"Zhang, Chunyuan"'
Biologically-inspired computing models have made significant progress in recent years, but the conventional von Neumann architecture is inefficient for the large-scale matrix operations and massive parallelism required by these models. This paper pre
Externí odkaz:
http://arxiv.org/abs/2404.02463
Autor:
Fu, Siqing, Li, Tiejun, Zhang, Chunyuan, Li, Hanqing, Ma, Sheng, Zhang, Jianmin, Zhang, Ruiyi, Wu, Lizhou
Publikováno v:
IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 31, no. 10, pp. 1578-1591, Oct. 2023
High-quality random numbers are very critical to many fields such as cryptography, finance, and scientific simulation, which calls for the design of reliable true random number generators (TRNGs). Limited by entropy source, throughput, reliability, a
Externí odkaz:
http://arxiv.org/abs/2312.17453
Publikováno v:
Gongye shui chuli, Vol 44, Iss 2, Pp 166-171 (2024)
The raw liquid and the bio-treatment(MBR) effluent of landfill leachate were irradiated using electron beam(EB) technology. The effect of EB irradiation on the molecular weight,organic composition of pollutants in the landfill leachate,as
Externí odkaz:
https://doaj.org/article/c183013ea16a4017b553a571243b3322
Autor:
Yang, Jianchao, Wen, Mei, Shen, Junzhong, Cao, Yasong, Tang, Minjin, Yang, Renyu, Fei, Jiawei, Zhang, Chunyuan
State-of-the-art systolic array-based accelerators adopt the traditional im2col algorithm to accelerate the inference of convolutional layers. However, traditional im2col cannot efficiently support AI backpropagation. Backpropagation in convolutional
Externí odkaz:
http://arxiv.org/abs/2209.09434
As an important algorithm in deep reinforcement learning, advantage actor critic (A2C) has been widely succeeded in both discrete and continuous control tasks with raw pixel inputs, but its sample efficiency still needs to improve more. In traditiona
Externí odkaz:
http://arxiv.org/abs/2201.05918
Convolutional neural networks (CNNs) have succeeded in many practical applications. However, their high computation and storage requirements often make them difficult to deploy on resource-constrained devices. In order to tackle this issue, many prun
Externí odkaz:
http://arxiv.org/abs/2201.04813
The echo state network (ESN) is a special type of recurrent neural networks for processing the time-series dataset. However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are difficult to
Externí odkaz:
http://arxiv.org/abs/2201.04781
Autor:
Xie, Jing, Liu, Xuhua, Wu, Biaoliang, Chen, Bochong, Song, Qiancheng, Guan, Yuan, Gong, Yuanxun, Yang, Chengliang, Lin, Jinbo, Huang, Mingfeng, Tan, Xinyu, Lai, Ruijun, Lin, Xiaozhen, Zhang, Sheng, Xie, Xiaoling, Chen, Xiaoli, Zhang, Chunyuan, Yang, Mei, Nong, Huijiao, Zhao, Xiaoyang, Xia, Laixin, Zhou, Weijie, Xiao, Guozhi, Jiang, Qing, Zou, Weiguo, Chen, Di, Lu, Di, Liu, Jia, Bai, Xiaochun
Publikováno v:
In Cell Reports Medicine 18 June 2024 5(6)
Recursive least squares (RLS) algorithms were once widely used for training small-scale neural networks, due to their fast convergence. However, previous RLS algorithms are unsuitable for training deep neural networks (DNNs), since they have high com
Externí odkaz:
http://arxiv.org/abs/2109.03220
Autor:
LI, Yancang1, ZHANG, Chunyuan1, ZHANG, Zihe1, SHI, Huawang1, FENG, Shenglei1 fengshenglei@hebeu.edu.cn
Publikováno v:
Materials Science / Medziagotyra. 2024, Vol. 30 Issue 1, p79-86. 8p.