Updated on 2022/08/19

 
ISHIBASHI Hideaki
 
Scopus Paper Info  
Total Paper Count: 0  Total Citation Count: 0  h-index: 2

Citation count denotes the number of citations in papers published for a particular year.

Affiliation
Graduate School of Life Science and Systems Engineering Department of Human Intelligence Systems
Job
Assistant Professor
External link

Degree

  • Kyushu Institute of Technology  -  Doctor of Information Engineering   2018.03

Biography in Kyutech

  • 2019.04
     

    Kyushu Institute of Technology   Graduate School of Life Science and Systems Engineering   Department of Human Intelligence Systems   Assistant Professor  

Papers

  • Principal Component Analysis for Gaussian Process Posteriors Reviewed International journal

    Ishibashi H., Akaho S.

    Neural Computation   34 ( 5 )   1189 - 1219   2022.04

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1162/neco_a_01489

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85129060990&origin=inward

  • Multi-task manifold learning for small sample size datasets Reviewed

    Ishibashi H., Higa K., Furukawa T.

    Neurocomputing   473   138 - 157   2022.02

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1016/j.neucom.2021.11.043

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85121311100&origin=inward

  • Automated stopping of spectral measurements with active learning Reviewed

    UENO Tetsuro, ISHIBASHI Hideaki, HINO Hideitsu, ONO Kanta

    Proceedings of the Annual Conference of JSAI ( The Japanese Society for Artificial Intelligence )   JSAI2022 ( 0 )   3Yin208 - 3Yin208   2022.01

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)

    <p>There is a need for improvement of the efficiency, automation, and autonomy of various experiments in materials science with the recent rise of materials informatics. We have developed a method to improve the efficiency of spectral measurements, one of general experimental techniques in materials science, by using active learning. By using active learning to sequentially measure the energy points with the maximum of the acquisition function, we have achieved automated spectral measurement under optimal conditions without the intervention of an experimenter. By employing a stopping criterion based on the upper bound of the expected generalization error of the Gaussian process regression, the measurement can be automatically stopped regardless of the type of spectrum. This method allows us to obtain the materials information of equivalent quality with fewer measurement points compared to the conventional spectral measurement.</p>

    DOI: 10.11517/pjsai.jsai2022.0_3yin208

    CiNii Research

  • Stopping criterion for Neural Architecture Search Reviewed

    SAKAMOTO Kotaro Sakamoto, ISHIBASHI Hideaki, SATO Rei, SHIRAKAWA Shinichi, AKIMOTO Yohei, HINO Hideitsu

    Proceedings of the Annual Conference of JSAI ( The Japanese Society for Artificial Intelligence )   JSAI2022 ( 0 )   3J4OS3b01 - 3J4OS3b01   2022.01

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)

    <p>Neural architecture search (NAS) is a framework for automating the design process of a neural network structure. While the recent one-shot approaches have reduced the search cost, there still exists an inherent trade-off between cost and performance. It is important to appropriately stop the search and further minimise the high cost of NAS. On the other hand, heuristic early-stopping strategies have been proposed to overcome the well-known performance degradation of the one-shot approach, particularly differentiable architecture search (DARTS). In this paper, we propose a more versatile and principled early-stopping criterion on the basis of the evaluation of a gap between expectation values of generalisation errors of the previous and current search steps with respect to the architecture parameters. The stopping threshold is automatically determined at each search epoch without cost. In numerical experiments, we demonstrate the effectiveness of the proposed method. We stop the one-shot NAS algorithms such as ASNG-NAS and DARTS and evaluate the acquired architectures on the benchmark datasets: NAS-Bench-201 and NATS-Bench. Our algorithm has been shown to reduce the cost of the search process while maintaining a high performance.</p>

    DOI: 10.11517/pjsai.jsai2022.0_3j4os3b01

    CiNii Research

  • Automated stopping criterion for spectral measurements with active learning Reviewed

    Ueno T., Ishibashi H., Hino H., Ono K.

    npj Computational Materials   7 ( 1 )   2021.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    The automated stopping of a spectral measurement with active learning is proposed. The optimal stopping of the measurement is realised with a stopping criterion based on the upper bound of the posterior average of the generalisation error of the Gaussian process regression. It is revealed that the automated stopping criterion of the spectral measurement gives an approximated X-ray absorption spectrum with sufficient accuracy and reduced data size. The proposed method is not only a proof-of-concept of the optimal stopping problem in active learning but also the key to enhancing the efficiency of spectral measurements for high-throughput experiments in the era of materials informatics.

    DOI: 10.1038/s41524-021-00606-5

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85113396806&origin=inward

  • Visual analytics of set data for knowledge discovery and member selection support Reviewed

    Watanabe R., Ishibashi H., Furukawa T.

    Decision Support Systems   152   2021.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1016/j.dss.2021.113635

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85111295128&origin=inward

  • Stopping criterion for active learning based on deterministic generalization bounds Reviewed International journal

    Hideaki Ishibashi, Hideitsu Hino

    Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics ( Proceedings of Machine Learning Research )   108   386 - 397   2020.08

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)

    Active learning is a framework in which the learning machine can select the samples to be used for training. This technique is promising, particularly when the cost of data acquisition and labeling is high. In active learning, determining the timing at which learning should be stopped is a critical issue. In this study, we propose a criterion for automatically stopping active learning. The proposed stopping criterion is based on the difference in the expected generalization errors and hypothesis testing. We derive a novel upper bound for the difference in expected generalization errors before and after obtaining a new training datum based on PAC-Bayesian theory. Unlike ordinary PAC-Bayesian bounds, though, the proposed bound is deterministic; hence, there is no uncontrollable trade-off between the confidence and tightness of the inequality. We combine the upper bound with a statistical test to derive a stopping criterion for active learning. We demonstrate the effectiveness of the proposed method via experiments with both artificial and real datasets.

  • Multi-task learning for Self-Organizing Maps Reviewed

    Kazushi Higa, Hideaki Ishibashi, Tetsuo Furukawa

    Proceedings of Joint 10th International Conference on Soft Computing and Intelligent Systems and19th International Symposium on Advanced Intelligent Systemsin conjunction with Intelligent Systems Workshop 2018   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

  • Non-parametriccontinuous Self-Organizing Map Reviewed

    Ryuji Watanabe, Hideaki Ishibashi, Tohru Iwasaki, Tetsuo Furukawa

    Proceedings of Joint 10th International Conference on Soft Computing and Intelligent Systems and19th International Symposium on Advanced Intelligent Systemsin conjunction with Intelligent Systems Workshop 2018   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

  • Multi-task manifold learning using hierarchical modeling for insufficient samples Reviewed

    Hideaki Ishibashi, Kazushi Higa, Tetsuo Furukawa

    Lecture Notes in Computer Science   11303   388 - 398   2018.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

    DOI: 10.1007/978-3-030-04182-3_34

  • Visualization method of viewpoints latent in a dataset Reviewed

    Hideaki Ishibashi

    Lecture Notes in Computer Science   11303   638 - 647   2018.11

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)

    DOI: 10.1007/978-3-030-04182-3_56

  • Hierarchical tensor SOM network for multilevel multigroup analysis Reviewed

    Hideaki Ishibashi, Tetsuo Furukawa)

    Proceedings of Neural Processing Letters   47 ( 3 )   1011 - 1025   2018.06

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1007/s11063-017-9643-1

  • Hierarchical Tensor Manifold Modeling for Multi-Group Analysis Reviewed

    ISHIBASHI Hideaki, ERA Masayoshi, FURUKAWA Tetsuo

    101 ( 11 )   1745 - 1755   2018.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1587/transfun.E101.A.1745

    CiNii Article

    Other Link: https://ci.nii.ac.jp/naid/130007502924

  • Multilevel-Multigroup Analysis Discovering Member Correspondence between Groups Reviewed

    Hideaki Ishibashi, Masayoshi Era, Ryota Shinriki, Hirohisa Isogai, Tetsuo Furukawa

    Proceedings of 2017 International Workshop on Smart Info-Media Systems in Asia   2017.09

     More details

    Language:English   Publishing type:Research paper (scientific journal)

  • Self-Organizing Maps for Multi-system and Multi-view Datasets "jointly worked" Reviewed

    Ishibashi H., Furukawa T.

    Proceedings - 2016 Joint 8th International Conference on Soft Computing and Intelligent Systems and 2016 17th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2016   343 - 348   2016.12

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)

    DOI: 10.1109/SCIS-ISIS.2016.0078

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85010366338&origin=inward

  • Multilevel-Multigroup analysis using a hierarchical tensor SOM network "jointly worked" Reviewed

    Hideaki Ishibashi, Ryota Shinriki, Hirohisa Isogai, Tetsuo Furukawa

    Lecture Notes in Computer Science   9949   459 - 466   2016.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

    DOI: 10.1007/978-3-319-46675-0_50

    Kyutacar

  • Self-Organizing maps for multi-system and multi-view datasets "jointly worked" Reviewed

    Hideaki Ishibashi, Tetsuo Furukawa

    Proceedings of Joint 8th International Conference on Soft Computing and Intelligent Systems and 17th International Symposium on AdvancedIntelligent Systems2016   343 - 348   2016.08

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

  • Rating-scale questionnaire survey analysis using SOM-based nonlinear tensor decomposition "jointly worked" Reviewed

    Hideaki Ishibashi, Tohru Iwasaki, Yohsuke Date, Tetsuo Furukawa

    Proceedings of Joint 8th International Conference on Soft Computing and Intelligent Systems and 17th International Symposium on Advanced Intelligent Systems2016   912 - 915   2016.08

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

▼display all

Lectures

  • 能動学習の停止基準

    第42回IBISML研究会オーガナイズドセッション  2021.03 

     More details

    Language:Japanese   Presentation type:Invited lecture  

Grants-in-Aid for Scientific Research

  • Energy based model集合のメタモデリング

    Grant number:22K17951  2022.04 - 2024.03   若手研究