Search Results for author: Weixia Xu

Found 7 papers, 1 papers with code

Molecular Property Prediction Based on Graph Structure Learning

no code implementations28 Dec 2023 Bangyi Zhao, Weixia Xu, Jihong Guan, Shuigeng Zhou

Following that, we conduct graph structure learning on the MSG (i. e., molecule-level graph structure learning) to get the final molecular embeddings, which are the results of fusing both GNN encoded molecular representations and the relationships among molecules, i. e., combining both intra-molecule and inter-molecule information.

Drug Discovery Graph structure learning +2

SeqXFilter: A Memory-efficient Denoising Filter for Dynamic Vision Sensors

no code implementations2 Jun 2020 Shasha Guo, Lei Wang, Xiaofan Chen, Limeng Zhang, Ziyang Kang, Weixia Xu

We not only give the visual denoising effect of the filter but also use two metrics for quantitatively analyzing the filter's performance.

Denoising

OD-SGD: One-step Delay Stochastic Gradient Descent for Distributed Training

1 code implementation14 May 2020 Yemao Xu, Dezun Dong, Weixia Xu, Xiangke Liao

To scale out to achieve faster training speed, two update algorithms are mainly applied in the distributed training process, i. e. the Synchronous SGD algorithm (SSGD) and Asynchronous SGD algorithm (ASGD).

A Noise Filter for Dynamic Vision Sensors using Self-adjusting Threshold

no code implementations8 Apr 2020 Shasha Guo, Ziyang Kang, Lei Wang, Limeng Zhang, Xiaofan Chen, Shiming Li, Weixia Xu

Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imagers.

Emerging Technologies Signal Processing

A Neural Architecture Search based Framework for Liquid State Machine Design

no code implementations7 Apr 2020 Shuo Tian, Lianhua Qu, Kai Hu, Nan Li, Lei Wang, Weixia Xu

By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity.

Neural Architecture Search

Exploration of Input Patterns for Enhancing the Performance of Liquid State Machines

no code implementations6 Apr 2020 Shasha Guo, Lianhua Qu, Lei Wang, Shuo Tian, Shiming Li, Weixia Xu

To mitigate the difficulty in effectively dealing with huge input spaces of LSM, and to find that whether input reduction can enhance LSM performance, we explore several input patterns, namely fullscale, scanline, chessboard, and patch.

Cannot find the paper you are looking for? You can Submit a new open access paper.