Shimauchi Hirokazu

シマウチヒロカズ | Shimauchi Hirokazu

Affiliation and department：
Job title： Associate Professor
Homepage URL (1)： https://sites.google.com/view/hirokazu-shimauchi

Research field (2)： High-performance computing , Applied mathematics and statistics

Research keywords (3)： Machine Learning , Deep Learning , Quasiconformal Mapping

Research theme for competitive and other funds (6)：

2022 - 2025 離散リーマン面の離散擬等角変形理論の基礎づけ
2022 - 2025 Constructing Highly Accurate Supervised Outlier Detection Method by Quasiconformal Extension and Generative Adversarial Networks
2020 - 2022 高精度かつ安定な深層学習のための確率的擬等角活性化関数の構築
2016 - 2018 Visualizaion of exteremal quasiconformal mappings
2013 - 2017 Potential theory on space complexity and ideal boundary

Show all

Papers (22)：

Hirokazu Shimauchi. Quasiconformal Extension-Based Unsupervised Representation Learning and Application to Semi-supervised Outlier detection. Accepted at Studies in Computational Intelligence, Lecture Notes in Computer Science, Springer. 2024
Hirokazu Shimauchi. Unsupervised Representation Learning by Quasiconformal Extension. Proceedings of the 15th International Joint Conference on Computational Intelligence. 2023
YUKI KAKIZAKI, YUKIKO SAKAI, HIROKAZU SHIMAUCHI. Reponses to tweets from physicians, experts, and governors during Covid-19 pandemic: An analysis using BERT. The Bulletin of Hachinohe Institute of Technology. 2023. 42
Hirokazu Shimauchi, Shinsuke Takase. Tsunami Forecasting from Sparse Observations by Semi-Supervised Outlier Detection with Generative Adversarial Network. 15th World Congress on Computational Mechanics & the 8th Asian Pacific Congress on Computational Mechanics. 2022
Hirokazu Shimauchi. An Activation Function with Probabilistic Beltrami Coefficient for Deep Learning. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence (Vienna, Austria, Online), Vol. 3, 613-620. 2022

ｍore...

Books (1)：

百科繚覧 Vol 1 : 若手研究者が挑む学際フロンティア
東北大学出版会 2019 ISBN:9784861633133

Lectures and oral presentations (26)：

量子カーネルを用いた教師なし表現学習によるXGBODの外れ値検出の性能向上
(電子情報通信学会データ工学研究会 2024)
クラリネット用リード画像を用いた演奏適性の評価における画像の入力に関する検討
(音楽音響研究会 2024)
区分線形擬等角写像と数値等角溶接による数値擬等角写像
(2023年度「等角写像論・値分布論」合同研究集会 2024)
Quasiconformal Mapping and its Application: Numerical Method and Application to Machine Learning
(電子情報通信学会スマートインフォメディアシステム研究会 2022)
等角写像の“指紋”と数値擬等角写像
(応用計算複素関数論(ACCA) One-day workshop 2021)

ｍore...

Works (1)：

Beltrami Equation Solver
2019 -

Professional career (1)：

Ph.D. in Information Sciences (Tohoku University)

Work history (10)：

2024/09 - 現在 Future University Hakodate Department of Complex and Intelligent Systems, School of Systems Information Science Associate Professor
2022/04 - 2024/08 Hachinohe Institute of Technology Faculty of Engineering, Department of System and Information Engineering Associate Professor
2020/04 - 2022/03 Hachinohe Institute of Technology Faculty of Engineering Department of System and Information Engineering Senior Assistant Professor
2018/09 - 2020/03 Tokyo foundation for policy research Policy Data Lab Data Scientist
2016/06 - 2020/03 Tokyo Institute of Technology School of Science

Show all

Committee career (11)：

2024/02 - 現在 16th International Conference on Emerging Networks and Systems Intelligence (Venice, Italy) Program Committee
2022/07 - 現在日本数学会雑誌「数学」編集委員
2023/03 - 2023/09 15th International Conference on Emerging Networks and Systems Intelligence (Porto, Portugal) Program Committee
2022/04 - 2022/11 14th International Conference on Emerging Networks and Systems Intelligence (Valencia, Spain) Program Committee
2021/11 - 2022/08 5th International Conference on Information Science and Systems (Beijing, China) Technical Committee

Show all

Awards (3)：

2024 - 青森県工業技術教育振興会奨励賞受賞擬等角拡張に基づく教師なし表現学習手法の構築
2023/12 - 15th International Joint Conference on Computational Intelligence (IJCCI 2023): Neural Computation Theory and Applications (NCTA 2023) Best Paper Candidates Unsupervised Representation Learning by Quasiconformal Extension
2019/12 - IEEE/ACM International Conference on Big Data Computing, Applications and Technologies Best Paper Candidates Topic Variation Detection Method for Detecting Political Business Cycles

Association Membership(s) (4)：

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS , THE MATHEMATICAL SOCIETY OF JAPAN , IEEE Computational Intelligence Society , ACM

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page