Zobrazeno 1 - 10
of 766
pro vyhledávání: '"LI Wenming"'
Autor:
Li Wenming
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
The purpose of designing a sports training fitness index monitoring system is to grasp better the physical performance data of athletes in the training process to ensure training safety. In this paper, the principle of multilayer perceptron is explai
Externí odkaz:
https://doaj.org/article/9026bc8a46f74cf2a69652b00bc4e7f0
Autor:
Li Wenming
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
In this paper, we study sports video classification technology based on a deep learning algorithm, using a convolutional neural network and deep learning gradient descent algorithm as the main research method to classify and regress the image feature
Externí odkaz:
https://doaj.org/article/9291ef068b68466e942a5f4ff19f33e2
Publikováno v:
Yankuang ceshi, Vol 42, Iss 3, Pp 598-615 (2023)
BACKGROUND Heavy metal pollution in soils is often the result of multiple genetic sources and action paths. Simple identification of the sources of heavy metals is not enough to provide sufficient information for the control of regional heavy metal p
Externí odkaz:
https://doaj.org/article/a13001e589644aadb3a6986506041a19
Autor:
Wu, Haibin, Li, Wenming, Yan, Kai, Fan, Zhihua, Liu, Tianyu, Liu, Yuqun, Liu, Yanhuan, Qiang, Ziqing, Ye, Xiaochun, Fan, Dongrui
Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced to reduce
Externí odkaz:
http://arxiv.org/abs/2411.00734
Autor:
Wu, Meng, Qiu, Jingkai, Yan, Mingyu, Li, Wenming, Zhang, Yang, Zhang, Zhimin, Ye, Xiaochun, Fan, Dongrui
Heterogeneous graph neural networks (HGNNs) are essential for capturing the structure and semantic information in heterogeneous graphs. However, existing GPU-based solutions, such as PyTorch Geometric, suffer from low GPU utilization due to numerous
Externí odkaz:
http://arxiv.org/abs/2408.08490
Characterizing graph neural networks (GNNs) is essential for identifying performance bottlenecks and facilitating their deployment. Despite substantial work in this area, a comprehensive survey on GNN characterization is lacking. This work presents a
Externí odkaz:
http://arxiv.org/abs/2408.01902
Recently, large language models (LLMs) have demonstrated excellent performance in understanding human instructions and generating code, which has inspired researchers to explore the feasibility of generating RTL code with LLMs. However, the existing
Externí odkaz:
http://arxiv.org/abs/2407.12022
Autor:
Xue, Runzhen, Han, Dengke, Yan, Mingyu, Zou, Mo, Yang, Xiaocheng, Wang, Duo, Li, Wenming, Tang, Zhimin, Kim, John, Ye, Xiaochun, Fan, Dongrui
Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the
Externí odkaz:
http://arxiv.org/abs/2307.12765
Heterogeneous graph neural networks (HGNNs) deliver powerful capacity in heterogeneous graph representation learning. The execution of HGNNs is usually accelerated by GPUs. Therefore, characterizing and understanding the execution pattern of HGNNs on
Externí odkaz:
http://arxiv.org/abs/2208.04758
Autor:
Sun, Gongjian, Yan, Mingyu, Wang, Duo, Li, Han, Li, Wenming, Ye, Xiaochun, Fan, Dongrui, Xie, Yuan
Limited by the memory capacity and compute power, singe-node graph convolutional neural network (GCN) accelerators cannot complete the execution of GCNs within a reasonable amount of time, due to the explosive size of graphs nowadays. Thus, large-sca
Externí odkaz:
http://arxiv.org/abs/2207.07258