Results 1 to 10 of about 18,832 (283)
Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 2023 The combustion method to obtain for pure graphitic carbon nitride (gCN) and two binary nanocomposites, gCN-Zn - gCN-Fe have been used in the present study.
Hasan Eskalen, Mustafa Kavgacı
doaj +4 more sources
Nano TrendsIn this study we presented the DFT based sensing of ethanol using pristine graphitic carbon nitride (gCN) and group-11 TM (Cu, Ag & Au) decorated gCN.
Nihal +5 more
exaly +4 more sources
ACE-GCN: A Fast Data-driven FPGA Accelerator for GCN Embedding
ACM Transactions on Reconfigurable Technology and Systems, 2021 ACE-GCN is a fast and resource/energy-efficient FPGA accelerator for graph convolutional embedding under data-driven and in-place processing conditions. Our accelerator exploits the inherent power law distribution and high sparsity commonly exhibited by real-world graphs datasets.
José Romero Hung +6 more
core +5 more sources
OD-GCN: Object Detection Boosted by Knowledge GCN [PDF]
2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2020 6 ...
Zheng Liu +3 more
openaire +3 more sources
Unified GCNs: Towards Connecting GCNs with CNNs
CoRR, 2022 Graph Convolutional Networks (GCNs) have been widely demonstrated their powerful ability in graph data representation and learning. Existing graph convolution layers are mainly designed based on graph signal processing and transform aspect which usually suffer from some limitations, such as over-smoothing, over-squashing and non-robustness, etc.
Ziyan Zhang, Bo Jiang 0002, Bin Luo 0001
openaire +2 more sources
MG-GCN: A Scalable multi-GPU GCN Training Framework
Proceedings of the 51st International Conference on Parallel Processing, 2022 12 pages, 13 figures, Under ...
Muhammed Fatih Balin +2 more
openaire +2 more sources
SPA-GCN: Efficient and Flexible GCN Accelerator with Application for Graph Similarity Computation [PDF]
Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, 2022 While there have been many studies on hardware acceleration for deep learning on images, there has been a rather limited focus on accelerating deep learning applications involving graphs. The unique characteristics of graphs, such as the irregular memory access and dynamic parallelism, impose several challenges when the algorithm is mapped to a CPU or ...
Atefeh Sohrabizadeh +2 more
openaire +2 more sources
Connection Science, 2022 The recognition of English texts in teaching scenes is a practical research direction. English text recognition can be widely used in English teaching scenes, such as assisting teachers to recognise students’ English homework, text positioning before ...
Mengyang Qin
doaj +1 more source
PPA-GCN: A Efficient GCN Framework for Prokaryotic Pathways Assignment
Frontiers in Genetics, 2022 With the rapid development of sequencing technology, completed genomes of microbes have explosively emerged. For a newly sequenced prokaryotic genome, gene functional annotation and metabolism pathway assignment are important foundations for all subsequent research work. However, the assignment rate for gene metabolism pathways is lower than 48% on the
Yuntao Lu, Yuntao Lu, Qi Li, Tao Li
openaire +3 more sources
Feature recommendation strategy for graph convolutional network
Connection Science, 2022 Graph Convolutional Network (GCN) is a new method for extracting, learning, and inferencing graph data that builds an embedded representation of the target node by aggregating information from neighbouring nodes.
Jisheng Qin +3 more
doaj +1 more source