Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Youhei Akimoto"'
Publikováno v:
IEEE Access, Vol 10, Pp 117501-117514 (2022)
We tackle explicitly constrained black-box continuous optimization problems in which the feasible domain forms a union of disconnected feasible subdomains. The decoder-based constraint-handling technique is a promising approach when the feasible doma
Externí odkaz:
https://doaj.org/article/9597e700c6dd4340b5990525bce630af
Publikováno v:
IEEE Access, Vol 10, Pp 101855-101868 (2022)
This study focuses on the domain generalization task, which aims to learn a model that generalizes to unseen domains by utilizing multiple training domains. More specifically, we follow the idea of adversarial data augmentation, which aims to synthes
Externí odkaz:
https://doaj.org/article/c5a118427b1240fe96fc2e41abb1b8f9
Autor:
Osamu Takyu, Shohei Fujii, Youhei Akimoto, Mai Ohta, Takeo Fujii, Fumihito Sasamori, Shiro Handa
Publikováno v:
International Journal of Distributed Sensor Networks, Vol 13 (2017)
Simultaneous data gathering is an application that exploits the unique advantages of wireless sensor networks. Because many sensor nodes access a channel, co-channel interference limits the number of nodes who can access it. To suppress co-channel in
Externí odkaz:
https://doaj.org/article/0c71781f3c5e477d89015d16e791e4d3
Publikováno v:
IEICE Transactions on Information and Systems. :523-537
In real-world applications of multi-class classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., speed limit). In this paper, we propose a loss function that can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b3523d9ca64d732ba7eaec8d59200e1
https://doi.org/10.1587/transinf.2022edp7200
https://doi.org/10.1587/transinf.2022edp7200
Publikováno v:
Journal of Marine Science and Technology. 27:1065-1083
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::408dfe5655d588a4b38d509dc2e8fe94
https://doi.org/10.1007/s00773-022-00889-3
https://doi.org/10.1007/s00773-022-00889-3
Autor:
Youhei Akimoto, Naoki Sakamoto
Publikováno v:
GECCO
We propose a novel constraint-handling technique for the covariance matrix adaptation evolution strategy (CMA-ES). The proposed technique is aimed at solving explicitly constrained black-box continuous optimization problems, in which the explicit con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7e07773736432f91877ee64b822099c
https://doi.org/10.1162/evco_a_00310
https://doi.org/10.1162/evco_a_00310
We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments: a simulator environment with semantics, that is, low-dimensional and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48b38559b0b8df09dbad6f1af90a94b2
http://arxiv.org/abs/2301.13343
http://arxiv.org/abs/2301.13343
Autor:
Youhei Akimoto
Surrogate functions are often employed to reduce the number of objective function evaluations in a continuous optimization. However, their effects have seldom been investigated theoretically. This paper analyzes the effect of a surrogate function in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15c54fe8d85ca86b3b93184300708e48
https://doi.org/10.21203/rs.3.rs-2095235/v1
https://doi.org/10.21203/rs.3.rs-2095235/v1
Autor:
Yasen Wang, Youhei Akimoto
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a79d0b97a484f0e71e6077d1380b7f2
https://doi.org/10.1145/3520304.3533971
https://doi.org/10.1145/3520304.3533971
Publikováno v:
Journal of Japan Society of Civil Engineers, Ser. A2 (Applied Mechanics (AM)). 77:21-34
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cec43ceddf81fec2c9513018a681ea9f
https://doi.org/10.2208/jscejam.77.1_21
https://doi.org/10.2208/jscejam.77.1_21