Results 21 to 30 of about 157,621 (267)
网络与信息安全学报, 2023 With the improvement of users’ security awareness and the development of encryption technology, encrypted traffic has become an important part of network traffic, and identifying encrypted traffic has become an important part of network traffic ...
Guozhen SHI +3 more
doaj +3 more sources
Bipartite graph capsule network [PDF]
World Wide Web, 2022 AbstractGraphs have been widely adopted in various fields, where many graph models are developed. Most of previous research focuses on unipartite or homogeneous graph analysis. In this graphs, the relationships between the same type of entities are preserved in the graphs.
Xianhang Zhang +5 more
openaire +1 more source
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 Convolutional neural networks (CNNs) have become a key asset to most of fields in AI. Despite their successful performance, CNNs suffer from a major drawback. They fail to capture the hierarchy of spatial relation among different parts of an entity. As a remedy to this problem, the idea of capsules was proposed by Hinton.
Marzieh Edraki +2 more
openaire +3 more sources
Research of Short Text Multi-intent Detection with Capsule Network
Jisuanji kexue yu tansuo, 2020 Intent detection is a key sub-task of spoken language understanding in human-machine dialogue system. Considering the problem of user's multi-intent expressed, a multi-intent classifier based on single-intent marker is constructed by using capsule ...
LIU Jiao, LI Yanling, LIN Min
doaj +1 more source
Capsule Network with Shortcut Routing
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2021 8 pages, published at IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences E104.A(8)
Thanh Vu Dang +3 more
openaire +3 more sources
Residual Capsule Network [PDF]
2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2019 Convolution Neural Network (CNN) has been the most influential innovations in the filed of Computer Vision. CNN have shown a substantial improvement in the field of Machine Learning. But they do come with their own set of drawbacks - CNN need a large dataset, hyperparameter tuning is nontrivial and importantly, they lose all the internal information ...
Sree Bala Shruthi Bhamidi +1 more
openaire +1 more source
How to Accelerate Capsule Convolutions in Capsule Networks
CoRR, 2021 How to improve the efficiency of routing procedures in CapsNets has been studied a lot. However, the efficiency of capsule convolutions has largely been neglected. Capsule convolution, which uses capsules rather than neurons as the basic computation unit, makes it incompatible with current deep learning frameworks' optimization solution.
Zhenhua Chen 0003 +3 more
openaire +2 more sources
Coal mine information comprehensive perception and intelligent decision system
Gong-kuang zidonghua, 2020 Aiming at problems of poor information perception ability and low decision level in coal mine safety production, a coal mine information comprehensive perception and intelligent decision system was proposed, which was composed of capsule network layer ...
LI Tengfei, LI Changyou, LI Jingzhao
doaj +1 more source
Capsule-LPI: a LncRNA–protein interaction predicting tool based on a capsule network
BMC Bioinformatics, 2021 Background Long noncoding RNAs (lncRNAs) play important roles in multiple biological processes. Identifying LncRNA–protein interactions (LPIs) is key to understanding lncRNA functions.
Ying Li +5 more
doaj +1 more source
Neural Processing Letters, 2020 Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter's invariance properties with equivariance through pose estimation. CapsNet achieved a very decent performance with a shallow architecture and a significant reduction in parameters count.
Mohammed Amer 0001, Tomás Maul
openaire +2 more sources