Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Xinglin Pan"'
Publikováno v:
Sensors, Vol 20, Iss 15, p 4349 (2020)
Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation th
Externí odkaz:
https://doaj.org/article/a32126f6548349108ab928d2d247f50c
Autor:
Xinglin Pan
Publikováno v:
Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::403cab313ba4d1486ad10579ba396da2
https://doi.org/10.1117/12.2667654
https://doi.org/10.1117/12.2667654
Publikováno v:
2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::66fcbc2d0908055aacf665852b7acfff
https://doi.org/10.1109/icdcs54860.2022.00051
https://doi.org/10.1109/icdcs54860.2022.00051
Publikováno v:
EUROPEAN JOURNAL OF MECHANICS B-FLUIDS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5033419b6ceefd54a56b5847b42e3cf
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 155
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Residual-like networks, such as ResNets, mainly focus on the skip connection to avoid gradient vanishing. However, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8249028aa32cf2bdcd71709fd6e135f
https://pubmed.ncbi.nlm.nih.gov/36115162
https://pubmed.ncbi.nlm.nih.gov/36115162
Publikováno v:
Sustainability; Volume 14; Issue 16; Pages: 10344
Intelligent vehicles refer to a new generation of vehicles with automatic driving functions that is gradually becoming an intelligent mobile space and application terminal by carrying advanced sensors and other devices and using new technologies, suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a929efef726ffaa3ffc09bbed9058011
https://doi.org/10.3390/su141610344
https://doi.org/10.3390/su141610344
The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new pote
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb0f6ca1d1a443bc89d0a3753fa05580
http://arxiv.org/abs/2101.00590
http://arxiv.org/abs/2101.00590
Publikováno v:
ACM Multimedia
In cloud and edge networks, federated learning involves training statistical models over decentralized data, where servers aggregate models through intermediate updates trained from clients. By utilizing private and local data it improves quality of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab83967746d8819de1ae677b6c4ec2e6
https://doi.org/10.1145/3394171.3413923
https://doi.org/10.1145/3394171.3413923
Publikováno v:
Asia-Pacific Journal of Regional Science. 1:63-84
This paper argues that China after decades of investment into creating self-innovation capacity with little success is finally making some significant progress. The evidence for this ranges from multiple technology companies entering the top ten list
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d230f3f5ca2b5334bd436099c267eb2d
https://doi.org/10.1007/s41685-017-0013-9
https://doi.org/10.1007/s41685-017-0013-9
Publikováno v:
SSRN Electronic Journal.
China has long wanted and envisioned the development of self-innovation as a means to drive its economy to one of the most productive in the world. Adopting this goal is a clear sign that China understands the Adam Smith and Schumpeterian argument th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3485c069d262c631b93b7c3b49f759ee
https://doi.org/10.2139/ssrn.2820864
https://doi.org/10.2139/ssrn.2820864