九州大学 研究者情報
研究者情報 (研究者の方へ)入力に際してお困りですか?
基本情報 研究活動 教育活動 社会活動
竹内 純一(たけうち じゆんいち) データ更新日:2023.11.27

教授 /  システム情報科学研究院 情報学部門 数理情報


主な研究テーマ
情報論的学習理論とその応用
キーワード:機械学習,情報理論,確率的コンプレキシティ,情報幾何,機械学習,超解像,サイバーセキュリティ,磁気共鳴画像法
2006.04.
研究業績
主要著書
1. Jun'ichi Takeuchi, ``An introduction to the minimum description length principle.''
(A chapter of ``A Mathematical Approach to Research Problems of Science and Technology,'' pp. 279-296,
Ryuei Nishii, Shin-ichiro Ei, Miyuki Koiso, Hiroyuki Ochiai, Kanzoh Okada, Shingo Saito, Tomoyuki Shira (editors))
, Springer, 2014.07.
2. 若山正人(編),小西貞則(著),竹内純一(著), 統計的モデリング/情報理論と学習理論, 講談社, 2008.09.
主要原著論文
1. Yoshinari Takeishi, Masazumi Iida, Junichi Takeuchi, Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks, Neural Networks, 164, 691-706, 2023.07, [URL].
2. T. He, C. Han, R. Isawa, T. Takahashi, S. Kijima, J. Takeuchi, Scalable and Fast Algorithm for Constructing Phylogenetic Trees with Application to IoT Malware Clustering, IEEE Access, 11, 8240-8253, 2023.01.
3. Chansu HAN, Jumpei SHIMAMURA, Takeshi TAKAHASHI, Daisuke INOUE, Jun'ichi TAKEUCHI, Koji NAKAO, Real-time Detection of Global Cyberthreat Based on Darknet by Estimating Anomalous Synchronization Using Graphical Lasso, IEICE Transactions, Vol.E103-D, No.10, 2020.10.
4. Masanori Kawakita, Jun'ichi Takeuchi, Minimum Description Length Principle in Supervised Learning With Application to Lasso, IEEE Transactions on Information Theory, 10.1109/TIT.2020.2998577, 66, 7, 4245-4269 , 2020.07, [URL].
5. Yoshinari Takeishi, Jun'ichi Takeuchi, An Improved Analysis of Least Squares Superposition Codes with Bernoulli Dictionary, Japanese Journal of Statistics and Data Science, Vol. 2, Issue 2, 2019.12, [URL].
6. Masanori Kawakita, Jun'ichi Takeuchi, A Note on Model Selection for Small Sample Regression, Machine Learning, 106, 11, 1839-1862, 2017.11.
7. Yoshinari Takeishi, Masanori Kawakita, Jun'ichi Takeuchi, Least Squares Superposition Codes with Bernoulli Dictionary are Still Reliable at Rates up to Capacity, IEEE Transactions on Information Theory, 60, 5, 2737-2750, 2014.05.
8. Masanori Kawakita, Jun'ichi Takeuchi, Safe Semi-supervised Learning Based on Weighted Likelihood, Neural Networks, 53, 146-164, 2014.05.
9. Jun'ichi Takeuchi, Tsutomu Kawabata, Andrew R. Barron, Properties of Jeffreys mixture of Markov Sources, IEEE transactions on Information Theory, 59, 1, 438-457, 2013.01.
10. J. Takeuchi & K. Yamanishi, A Unifying Framework for Detecting Outliers and Change Points from Non-Stationary Time Series Data, IEEE transactions on Knowledge and Data Engineering, Vol. 18, No. 4, pp.482-489, 2006.04.
11. J. Takeuchi & S. Amari, α-Parallel Prior and Its Properties, IEEE transactions on Information Theory, Vol. 51, No. 3, pp. 1011-1023, 2005.03.
12. K. Yamanishi, J. Takeuchi, G. Williamas, & P. Milne, On-line Unsupervised Oultlier Detection Using Finite Mixtures with Discounting Learning Algorithms, Data Mining and Knowleged Discovery Journal, 8 (3): 275-300, 2004.05.
13. J. Takeuchi, N. Abe, & S. Amari, The Lob-Pass problem, Journal of Computer and System Sciences, 2000.03.
14. J. Takeuchi, Characterization of the Bayes estimator and the MDL estimator for exponential families, IEEE transactions on Information Theory, Vol. 43, No. 4, pp. 1165-1174, 1997, 1997.01.
主要総説, 論評, 解説, 書評, 報告書等
主要学会発表等
1. M. Iida, Y. Takeishi, J. Takeuchi, On Fisher Information Matrix for Simple Neural Networks With Softplus Activation, The 2022 IEEE International Symposium on Information Theory, 2022.07.
2. C. Han, J. Takeuchi, T. Takahashi, D. Inoue, Automated Detection of Malware Activities Using Nonnegative Matrix Factorization, The 20th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 2021.10.
3. R. Kawasoe, C. Han, R. Isawa, T. Takahashi and J. Takeuchi, Investigating Behavioral Differences between IoT Malware via Function Call Sequence Graphs, he 36th ACM/SIGAPP Symposium On Applied Computing, 2021.03.
4. Kohei Miyamoto, Jun'ichi Takeuchi, On MDL Estimation for Simple Contaminated Gaussian Location Families, The International Symposium on Information Theory and Its Applications 2020, 2020.10.
5. Shizen Kitazaki, Masanori Kawakita, Yutaka Jitsumatsu, Shigehide Kuhara, Akio Hiwatashi, Jun'ichi Takeuchi, Magnetic Resonance Angiography Image Restoration by Super Resolution Based on Deep Learning, The 2019 World Congress of the European Society for Magnetic Resonance in Medicine and Biology, 2019.10.
6. Chansu Han, Jumpei Shimamura, Takeshi Takahashi, Daisuke Inoue, Masanori Kawakita, Jun'ichi Takeuchi, Koji Nakao, Real-Time Detection of Malware Activities by Analyzing Darknet Traffic Using Graphical Lasso, The 18th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 2019.08.
7. Kazushi Mimura, Jun'ichi Takeuchi, Dynamics of Damped Approximate Message Passing Algorithms, 2019 IEEE Information Theory Workshop, 2019.08.
8. Kohei Miyamoto, Andrew R. Barron, Jun'ichi Takeuchi, Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families, 2019 IEEE International Sympojium on Information Theory, 2019.07.
9. Jun'ichi Takeuchi, Hiroshi Nagaoka, Information Geometry of The Family of Markov Kernels Defined by A Context Tree, 2017 IEEE Information Theory Workshop, 2017.10.
10. Shoma Tanaka, Yuki Kawamura, Masanori Kawakita, Jun'ichi Takeuchi, MDL criterion for NMF with Application to Botnet Detection, the 2016 Data Mining and Cybersecurity Workshop, associated with the 23rd International Conference on Neural Information Processing,, 2016.10.
11. Chan-su Han, Kento Kono, Masanori Kawakita, Jun'ichi Takeuchi, Botnet Detection Using Graphical Lasso with Graph Density, the 2016 Data Mining and Cybersecurity Workshop, associated with the 23rd International Conference on Neural Information Processing,, 2016.10.
12. Yoshinari Takeishi, Jun'ichi Takeuchi, An Improved Upper Bound on Block Error Probability of Least Squares Superposition Codes with Unbiased Bernoulli Dictionary, 2016 IEEE International Symposium on Information Theory, 2016.07.
13. Masanori Kawakita, Jun'ichi Takeuchi, Barron and Cover's Theory in Supervised Learning and Its Application to Lasso, The 33rd International Conference on Machine Learning, 2016.06.
14. Jun'ichi Takeuchi, Andrew R. Barron, Stochastic complexity for tree models, 2014 IEEE Information Theory Workshop, 2014.11.
15. Jun'ichi Takeuchi, Andrew R. Barron, Asymptotically minimax regret for models with hidden variables, 2014 IEEE International Symposium on Information Theory, 2014.07.
16. Jun'ichi Takeuchi, Andrew R. Barron, Asymptotically Minimax Regret by Bayes Mixtures for Non-exponential Families, 2013 IEEE Information Theory Workshop, 2013.09.
17. Yoshinari Takeishi, Masanori Kawakita, Jun'ichi Takeuchi, Least Squares Superposition Codes with Bernoulli Dictionary are Still Reliable at Rates up to Capacity, 2013 IEEE International Symposium on Information Theory, 2013.07.
18. Sayaka Yamauchi, Masanori Kawakita, Jun'ichi Takeuchi, Botnet Detection based on Non-negative Matrix Factorization and the MDL Principle, the 19th International Conference on Neural Information Processing, 2012.11.
19. Jun'ichi Takeuchi, Yoshinari Takeishi, Sparse Superposition Codes with Discrete Dictionary, The 5th Workshop on Information Theoretic Methods in Science and Engineering, 2012.08.
20. Mariko Tsurusaki, Jun'ichi Takeuchi, Constant Markov Portfolio and Its Application to Universal Portfolio with Side Information, 2012 IEEE International Symposium on Information Theory, 2012.07.
21. Mariko Tsurusaki, Jun'ichi Takeuchi, Stochastic Interpretation of Universal Portfolio and Generalized Target Classes, 2011 IEEE International Symposium on Information Theory, 2011.08.
22. Jun'ichi Takeuchi, Stochastic Complexity and Exponential Curvature, The Fourth Workshop on Information Theoretic Methods in Science and Engineering, 2011.08.
23. Takeuchi, Fisher Information Determinant and Stochastic complexity for Markov Models, 2009 IEEE International Symposium on Information Theory, 2009.07.
24. Takeuchi, Kawabata, Exponential Curvature of Markov Sources, 2007 IEEE International Symposium on Information Theory, 2007.06.
学会活動
所属学会名
IEEE (Information Theory Society)
電子情報通信学会
日本応用数理学会
学協会役員等への就任
2013.05~2014.05, 電子情報通信学会情報理論研究専門委員会, 専門委員長.
2010.05~2012.05, 情報理論とその応用学会, 評議員.
2008.05~2010.05, 情報理論とその応用学会, 理事.
2010.05~2012.05, 電子情報通信学会情報論的学習理論と機械学習研究専門委員会, 専門委員.
2009.05~2010.03, 電子情報通信学会情報論的学習理論時限研究専門委員会, 委員長.
2008.05~2010.05, 情報理論とその応用学会, 編集理事.
2007.05~2009.05, 電子情報通信学会情報論的学習理論時限研究専門委員会, 副委員長.
2005.05~2006.05, 電子情報通信学会情報論的学習理論時限研究専門委員会, 幹事.
学会大会・会議・シンポジウム等における役割
2013.08.30~2013.08.30, Workshop on Modern Error Correcting Codes , Organizer.
2013.08.26~2013.08.29, The Sixth Workshop on Information Theoritic Methods in Science and Engineering (WITMSE2013), Local Co-Chair.
2012.12.11~2012.12.14, 第35回情報理論とその応用シンポジウム, 実行委員長.
2009.10~2009.10, 第12回情報論的学習理論ワークショップ, 実行委員長.
2007.11~2007.11, 第10回情報論的学習理論ワークショップ, プログラム委員長.
学会誌・雑誌・著書の編集への参加状況
2019.05, International Journal of Mathematics for Industry, 国際, 編集委員.
2014.05~2019.04, Pacific Journal of Mathematics for Industry, 国際, 編集委員.
2005.05~2008.05, 電子情報通信学会和文論文誌(A), 国内, 編集委員.
その他の研究活動
海外渡航状況, 海外での教育研究歴
Yale University, UnitedStatesofAmerica, 1996.09~1997.09.
受賞
SITA奨励賞, 情報理論とその応用学会, 1998.01.
先端技術大賞フジサンケイビジネスアイ賞, 2005.05.
研究資金
科学研究費補助金の採択状況(文部科学省、日本学術振興会)
2023年度~2027年度, 基盤研究(S), 代表, Fisher情報行列と記述長最小原理に基づく深層学習の理論と実践.
2022年度~2024年度, 基盤研究(C), 分担, 冠動脈静止期間自動抽出技術と超解像技術による高精細冠動脈MRA撮像技術の研究.
2018年度~2020年度, 基盤研究(B), 代表, 記述長最小原理の深化と応用.
2016年度~2018年度, 挑戦的萌芽研究, 分担, 圧縮センシングのダンピング付き反復再構成法の解析と応用.
2012年度~2014年度, 基盤研究(C), 代表, 記述長最小原理の数理と学習理論.
2007年度~2010年度, 基盤研究(B), 代表, 情報量概念を基盤とした学習理論の展開.
競争的資金(受託研究を含む)の採択状況
2008年度~2012年度, 研究拠点形成費補助金(グローバルCOE) (文部科学省), 分担, マス・フォア・インダストリ.

九大関連コンテンツ

pure2017年10月2日から、「九州大学研究者情報」を補完するデータベースとして、Elsevier社の「Pure」による研究業績の公開を開始しました。