CSpace

浏览/检索结果: 共5条,第1-5条 帮助

已选(0)清除 条数/页:   排序方式:
CompSNN: A lightweight spiking neural network based on spatiotemporally compressive spike features 期刊论文
NEUROCOMPUTING, 2021, 卷号: 425, 页码: 96-106
作者:  Wang, Tengxiao;  Shi, Cong;  Zhou, Xichuan;  Lin, Yingcheng;  He, Junxian;  Gan, Ping;  Li, Ping;  Wang, Ying;  Liu, Liyuan;  Wu, Nanjian;  Luo, Gang
收藏  |  浏览/下载:39/0  |  提交时间:2021/12/01
Neuromorphic computing  Spiking neural networks  SNN  Compressive sensing  Object classification  Multi-spike encoding  
A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification 期刊论文
SENSORS, 2020, 卷号: 20, 期号: 17, 页码: 18
作者:  He, Wei;  Huang, Jinguo;  Wang, Tengxiao;  Lin, Yingcheng;  He, Junxian;  Zhou, Xichuan;  Li, Ping;  Wang, Ying;  Wu, Nanjian;  Shi, Cong
收藏  |  浏览/下载:55/0  |  提交时间:2020/12/10
address-event representation (AER)  Random Ferns  object classification  neuromorphic hardware  online learning  on-chip learning  
A review of the application of deep learning in medical image classification and segmentation 期刊论文
ANNALS OF TRANSLATIONAL MEDICINE, 2020, 卷号: 8, 期号: 11, 页码: 15
作者:  Cai, Lei;  Gao, Jingyang;  Zhao, Di
收藏  |  浏览/下载:47/0  |  提交时间:2020/12/10
Big medical data  deep learning  classification  segmentation  object detection  
Object Categorization Using Class-Specific Representations 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 9, 页码: 4528-4534
作者:  Zhang, Chunjie;  Cheng, Jian;  Li, Liang;  Li, Changsheng;  Tian, Qi
收藏  |  浏览/下载:51/0  |  提交时间:2019/12/10
Class-specific representation  image classification  object categorization  visual representation  
Implicit Negative Sub-Categorization and Sink Diversion for Object Detection 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 卷号: 27, 期号: 4, 页码: 1561-1574
作者:  Li, Yu;  Tang, Sheng;  Lin, Min;  Zhang, Yongdong;  Li, Jintao;  Yan, Shuicheng
收藏  |  浏览/下载:68/0  |  提交时间:2019/12/10
Object detection  convolutional neural network  faster R-CNN  classification loss  context information