Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Gyeong-Moon Park"'
Publikováno v:
Remote Sensing, Vol 16, Iss 12, p 2054 (2024)
Fisheye cameras play a crucial role in various fields by offering a wide field of view, enabling the capture of expansive areas within a single frame. Nonetheless, the radial distortion characteristics of fisheye lenses lead to notable shape deformat
Externí odkaz:
https://doaj.org/article/52b3cb2edff64048b1243fa263e0d2b9
Publikováno v:
IEEE Access, Vol 11, Pp 74035-74047 (2023)
Time series anomaly detection is a task that determines whether an unseen signal is normal or abnormal, and it is a crucial function in various real-world applications. Typical approach is to learn normal data representation using generative models,
Externí odkaz:
https://doaj.org/article/a4acb3878c2e49d9b998250956f09001
Autor:
Gyeong-Moon Park, Jong-Hwan Kim
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 32:4347-4361
Adaptive resonance theory (ART) networks, including developmental resonance network (DRN), basically use a vigilance parameter as a hyperparameter to determine whether a current input can belong to any existing categories or not. The problem here is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e1f08fae36bd228b4f91e950bc595db
https://doi.org/10.1109/tnnls.2020.3017490
https://doi.org/10.1109/tnnls.2020.3017490
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 32:2691-2705
Convolutional neural networks (CNNs) are one of the most successful deep neural networks. Indeed, most of the recent applications related to computer vision are based on CNNs. However, when learning new tasks in a sequential manner, CNNs face catastr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25d97b0ae9ecfaeeadf899de563227fa
https://doi.org/10.1109/tnnls.2020.3007548
https://doi.org/10.1109/tnnls.2020.3007548
Autor:
Seung-Jun Moon, Gyeong-Moon Park
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197833
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c359b1df39679353bb9bc9365202d058
https://doi.org/10.1007/978-3-031-19784-0_27
https://doi.org/10.1007/978-3-031-19784-0_27
Autor:
Gyeong-Moon, Park, Yong-Ho, Yoo, Deok-Hwa, Kim, Jong-Hwan, Kim, Gyeong-Moon Park, Yong-Ho Yoo, Deok-Hwa Kim, Jong-Hwan Kim
Publikováno v:
IEEE Transactions on Cybernetics. 48:1786-1799
Robots are expected to perform smart services and to undertake various troublesome or difficult tasks in the place of humans. Since these human-scale tasks consist of a temporal sequence of events, robots need episodic memory to store and retrieve th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f17b82aed4eb196fbb0efa854a6d9ae5
https://doi.org/10.1109/tcyb.2017.2715338
https://doi.org/10.1109/tcyb.2017.2715338
Publikováno v:
IEEE transactions on cybernetics. 52(10)
An intelligent robot requires episodic memory that can retrieve a sequence of events for a service task learned from past experiences to provide a proper service to a user. Various episodic memories, which can learn new tasks incrementally without fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a2b56f13d0730459088ad9d2ccde5bfd
https://pubmed.ncbi.nlm.nih.gov/34133306
https://pubmed.ncbi.nlm.nih.gov/34133306
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 30:1278-1284
Adaptive resonance theory (ART) networks deal with normalized input data only, which means that they need the normalization process for the raw input data, under the assumption that the upper and lower bounds of the input data are known in advance. W
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4890e4793ec080d5c8dca21ba31ec67
https://doi.org/10.1109/tnnls.2018.2863738
https://doi.org/10.1109/tnnls.2018.2863738
Publikováno v:
IEEE Transactions on Emerging Topics in Computational Intelligence. 1:41-50
The crux of the realization of task intelligence for robots is to design the memory module for storing temporal event sequences of tasks, the mechanism of thought for reasoning, and motion planning methodology for execution, among others. In this pap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0868e9ce1136866c158e9e37c9c44514
https://doi.org/10.1109/tetci.2016.2645720
https://doi.org/10.1109/tetci.2016.2645720
Publikováno v:
Annual Reviews in Control. 44:9-18
In order to perform various tasks using a robot in a real environment, it is necessary to learn the tasks based on recognition, to be able to derive a task sequence suitable for the situation, and to be able to generate a behavior adaptively. To deal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::346a4f6b4bac055eeccd89939c7ec214
https://doi.org/10.1016/j.arcontrol.2017.09.013
https://doi.org/10.1016/j.arcontrol.2017.09.013