no code implementations • 14 Jul 2023 • Changqing Xu, Yi Liu, YinTang Yang
Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest due to their low power features, high biological plausibility, and strong spatiotemporal information processing capability.
no code implementations • 31 Jul 2022 • Changqing Xu, Yijian Pei, Zili Wu, Yi Liu, YinTang Yang
Spiking neural network (SNN) is a brain-inspired model which has more spatio-temporal information processing capacity and computational energy efficiency.
no code implementations • 18 Mar 2022 • Changqing Xu, Yi Liu, YinTang Yang
We evaluate the proposed method for event streams classification tasks on neuromorphic N-MNIST, CIFAR10-DVS, DVS128 gesture datasets.
no code implementations • 25 Jan 2022 • Dongrui Liu, Chuanchuan Chen, Changqing Xu, Robert Qiu, Lei Chu
In this paper, we propose to jointly use both global and local descriptors to register point clouds in a self-supervised manner, which is motivated by a critical observation that all local geometries of point clouds are transformed consistently under the same transformation.
no code implementations • 25 Nov 2021 • Changqing Xu, Yi Liu, YinTang Yang
In our proposed training method, we proposed three approximated derivative for spike activity to solve the problem of the non-differentiable issue which cause difficulties for direct training SNNs based on BP.
no code implementations • 22 May 2021 • Changqing Xu, Yi Liu, XinFang Liao, JiaLiang Cheng, YinTang Yang
A multilayer feedfordward neural network is used to build the SET pulse current model by learning the data from TCAD simulation.
no code implementations • 17 Feb 2021 • Changqing Xu, Zeguo Chen, Guanqing Zhang, Guancong Ma, Ying Wu
The recent discovery and realizations of higher-order topological insulators enrich the fundamental studies on topological phases.
Applied Physics
1 code implementation • 15 Sep 2020 • Dongrui Liu, Chuanchuan Chen, Changqing Xu, Qi Cai, Lei Chu, Fei Wen, Robert Caiming Qiu
We prove that CAT is a rotation and translation-invariant transformation based on the theoretical analysis.
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.