no code implementations • 25 Jan 2021 • Shibo Zhou, Yu Pan
Since time series always contains a lot of noise, which has a negative impact on network training, people usually filter the original data before training the network.
no code implementations • 21 Jan 2021 • Shibo Zhou, Wei Wang, Xiaohua LI, Zhanpeng Jin
The proposed temporal coding scheme maps each event's arrival time and data into SNN spike time so that asynchronously-arrived events are processed immediately without delay.
no code implementations • 15 Oct 2020 • Shibo Zhou, Xiaohua LI
To support this claim, we show that SNNs built with nonleaky neurons can have a less-complex and less-nonlinear input-output response.
no code implementations • 24 Jan 2020 • Wei Wang, Shibo Zhou, Jingxi Li, Xiaohua LI, Junsong Yuan, Zhanpeng Jin
Accurate real-time object recognition from sensory data has long been a crucial and challenging task for autonomous driving.
no code implementations • 17 Dec 2019 • Shibo Zhou, Ying Chen, Xiaohua LI, Arindam Sanyal
In this paper, we integrate spiking convolutional neural network (SCNN) with temporal coding into the YOLOv2 architecture for real-time object detection.
1 code implementation • 24 Sep 2019 • Shibo Zhou, Xiaohua LI, Ying Chen, Sanjeev T. Chandrasekaran, Arindam Sanyal
Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency.
no code implementations • 29 Oct 2018 • Shibo Zhou, Wei Wang
Neural networks has been successfully used in the processing of Lidar data, especially in the scenario of autonomous driving.