Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Zhenzhi Wu"'
Autor:
Zhenzhi Wu, Yangshu Shen, Jing Zhang, Huaju Liang, Rongzhen Zhao, Han Li, Jianping Xiong, Xiyu Zhang, Yansong Chua
Publikováno v:
Frontiers in Neuroscience, Vol 17 (2023)
Brain-inspired deep spiking neural network (DSNN) which emulates the function of the biological brain provides an effective approach for event-stream spatiotemporal perception (STP), especially for dynamic vision sensor (DVS) signals. However, there
Externí odkaz:
https://doaj.org/article/0b1c03889fe64c1c872d47d14ec25be0
Autor:
Rong Zhao, Zheyu Yang, Hao Zheng, Yujie Wu, Faqiang Liu, Zhenzhi Wu, Lukai Li, Feng Chen, Seng Song, Jun Zhu, Wenli Zhang, Haoyu Huang, Mingkun Xu, Kaifeng Sheng, Qianbo Yin, Jing Pei, Guoqi Li, Youhui Zhang, Mingguo Zhao, Luping Shi
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-12 (2022)
Hybrid neural networks combine advantages of spiking and artificial neural networks in the context of computing and biological motivation. The authors propose a design framework with hybrid units for improved flexibility and efficiency of hybrid neur
Externí odkaz:
https://doaj.org/article/c41e7262657143f7aa89477cd794864b
Publikováno v:
IEEE Access, Vol 8, Pp 98562-98571 (2020)
3D object detection and recognition are crucial tasks for many spatiotemporal processing applications, such as computer-aided diagnosis and autonomous driving. Although prevalent 3D Convolution Nets (ConvNets) have continued to improve the accuracy a
Externí odkaz:
https://doaj.org/article/46e9ed5c43b842968fb47adb658640f4
Publikováno v:
E3S Web of Conferences, Vol 236, p 05014 (2021)
With the advent of the Internet Age, the rapid development of modern rural construction and urban-rural integration, the revival of traditional culture and environmental improvement and many other factors, the multi-semantic social relationship of th
Externí odkaz:
https://doaj.org/article/a8b0e0823fac466aa3fbeac19d805064
Existing convolution techniques in artificial neural networks suffer from huge computation complexity, while the biological neural network works in a much more powerful yet efficient way. Inspired by the biological plasticity of dendritic topology an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aab90bf262aab6c93f522c739bdd3402
http://arxiv.org/abs/2301.05440
http://arxiv.org/abs/2301.05440
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6636c699b9d4ee389ed58c4637006a85
https://doi.org/10.1109/cvpr52688.2022.00073
https://doi.org/10.1109/cvpr52688.2022.00073
Autor:
Xing Hu, Lei Deng, Guoqi Li, Ling Liang, Maohua Zhu, Luping Shi, Zhenzhi Wu, Guanrui Wang, Shuangchen Li, Yujie Wu, Z. Yang, Yuan Xie, Wei He, Zhe Zou, Jing Pei, Yufei Ding
Publikováno v:
IEEE Journal of Solid-State Circuits. 55:2228-2246
Toward the long-standing dream of artificial intelligence, two successful solution paths have been paved: 1) neuromorphic computing and 2) deep learning. Recently, they tend to interact for simultaneously achieving biological plausibility and powerfu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::668674d112a471896cb3e8d2e381ec06
https://doi.org/10.1109/jssc.2020.2970709
https://doi.org/10.1109/jssc.2020.2970709
Publikováno v:
IEEE Access, Vol 8, Pp 98562-98571 (2020)
3D object detection and recognition are crucial tasks for many spatiotemporal processing applications, such as computer-aided diagnosis and autonomous driving. Although prevalent 3D Convolution Nets (ConvNets) have continued to improve the accuracy a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41d1e883988cb00693c011de76c64dd9
https://doi.org/10.1109/access.2020.2995886
https://doi.org/10.1109/access.2020.2995886
Autor:
Rong Zhao, Zheyu Yang, Hao Zheng, Yujie Wu, Faqiang Liu, Zhenzhi Wu, Lukai Li, Feng Chen, Seng Song, Jun Zhu, Wenli Zhang, Haoyu Huang, Mingkun Xu, Kaifeng Sheng, Qianbo Yin, Jing Pei, Guoqi Li, Youhui Zhang, Mingguo Zhao, Luping Shi
Publikováno v:
Nature communications. 13(1)
There is a growing trend to design hybrid neural networks (HNNs) by combining spiking neural networks and artificial neural networks to leverage the strengths of both. Here, we propose a framework for general design and computation of HNNs by introdu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36ede734e5ea9d2800f4825af851c7f1
https://pubmed.ncbi.nlm.nih.gov/35701391
https://pubmed.ncbi.nlm.nih.gov/35701391
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 149
Bio-inspired recipes are being introduced to artificial neural networks for the efficient processing of spatio-temporal tasks. Among them, Leaky Integrate and Fire (LIF) model is the most remarkable one thanks to its temporal processing capability, l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6cab8f5bf8a9900cdc7e1799497d571
https://pubmed.ncbi.nlm.nih.gov/35248808
https://pubmed.ncbi.nlm.nih.gov/35248808