1 code implementation • 20 May 2022 • Wenrui Zhang, Ling Yang, Shijia Geng, Shenda Hong
In this paper, we aim at learning representations for time series from a new perspective and propose Cross Reconstruction Transformer (CRT) to solve the aforementioned problems in a unified way.
1 code implementation • 26 Feb 2022 • Wenrui Zhang, Xinxin Di, Guodong Wei, Shijia Geng, Zhaoji Fu, Shenda Hong
Finally, with the help of a clinician, we conduct case studies to explain the results of large uncertainties and incorrect predictions with small uncertainties.
no code implementations • 25 Feb 2022 • Wenrui Zhang, Shijia Geng, Shenda Hong
To verify the effectiveness of the proposed method, we perform a downstream task to detect atrial fibrillation (AF) which is one of the most common ECG tasks.
no code implementations • 25 Feb 2022 • Wenrui Zhang, Shijia Geng, Zhaoji Fu, Linlin Zheng, Chenyang Jiang, Shenda Hong
MAML is expected to better transfer the knowledge from a large dataset and use only a few recordings to quickly adapt the model to a new person.
no code implementations • 4 Aug 2021 • Wenrui Zhang, Hejia Geng, Peng Li
The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes.
no code implementations • 22 Jun 2021 • Yukun Yang, Wenrui Zhang, Peng Li
While backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a continuous-valued loss over layers of spiking neurons exhibiting discontinuous all-or-none firing activities.
no code implementations • 23 Oct 2020 • Wenrui Zhang, Peng Li
Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters.
1 code implementation • NeurIPS 2020 • Wenrui Zhang, Peng Li
Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors.
no code implementations • 10 Sep 2019 • Changqing Xu, Wenrui Zhang, Yu Liu, Peng Li
Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15. 93x, 13. 88x, and 86. 21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA.
1 code implementation • NeurIPS 2019 • Wenrui Zhang, Peng Li
However, the practical application of RSNNs is severely limited by challenges in training.
no code implementations • 25 Apr 2019 • Binghan Li, Wenrui Zhang, Mi Lu
The RESIDE dataset provides enough synthetic hazy images and their corresponding groundtruth images to train and test.
no code implementations • 29 Jan 2019 • Myung Seok Shim, Chenye Zhao, Yang Li, Xuchong Zhang, Wenrui Zhang, Peng Li
Sensor fusion has wide applications in many domains including health care and autonomous systems.
1 code implementation • NeurIPS 2018 • Yingyezhe Jin, Wenrui Zhang, Peng Li
We evaluate the proposed HM2-BP algorithm by training deep fully connected and convolutional SNNs based on the static MNIST [14] and dynamic neuromorphic N-MNIST [26].