Skip to content
Global
Japanese
Site Map
Global
Contact Us
Japanese
Site Map
Global
Contact Us

Advanced Devices R&D Center

Yasutaka FURUSHO

Yasutaka FURUSHO

Ph. D in Engineering
Analytics AI R&D Dept.

Research Area:

  • ● Machine Learning
  • ● Computer Vision

Papers/Conference Talks:

  • ● Y. Furusho, Y. Sakata, and S. Nitta, "Kernel Ridge Reconstruction for Anomaly Detection: General and Low Computational Reconstruction", International Conference on Machine Learning and Applications, 2021.
  • ● Y. Furusho and K. Ikeda, "ResNet and Batch-normalization Improve Data Separability", Asian Conference on Machine Learning, 2019.
  • ● Y. Furusho and K. Ikeda, "Generation and Visualization of Tennis Swing Motion by Conditional Variational RNN with Hidden Markov Model", Asian Conference on Machine Learning: Trajectory, Activity, and Behavior workshop, 2019.
  • ● Y. Furusho and K. Ikeda, "Theoretical Analysis of the Fixup Initialization for Fast Convergence and High Generalization Ability", International Conference on Machine Learning: Generalization in Deep Learning workshop, 2019.
  • ● Y. Furusho and K. Ikeda, "Additive or Concatenating Skip-connection Improve Data Separability", International Conference on Machine Learning: Generalization in Deep Learning workshop, 2019.
  • ● Y. Furusho and K. Ikeda, "Effects of Skip-connection in ResNet and Batch-normalization on Fisher Information Matrix", INNS Big Data and deep learning, 2019.
  • ● Y. Furusho, T. Liu, and K. Ikeda, "Skipping two layers in ResNet Makes the Generalization Gap Smaller than Skipping one or no layers", INNS Big Data and deep learning, 2019.
  • ● Y. Furusho and K. Ikeda, "Non-asymptotic analysis of Fisher information matrices of Multi-layer perceptron, ResNet, and Batch-normalization", INCF Advances in Neuroinformatics, 2018.
  • ● Y. Furusho, T. Kubo, and K. Ikeda, "Information Theoretical Analysis of Deep Learning Representations", International Conference on Neural Information Processing, 2015.
  • ● Y. Furusho and K. Kiyota, "A Multiuser Rehabilitation System Using Virtual World for the Elderly", International Symposium on Technology for Sustainability, 2013.

Journals:

  • ● Y. Furusho, Shuhei Nitta, and Yukinobu Sakata, "Anomaly Detection and Debugging by Kernel Ridge Reconstruction", Deep Learning Applications, Volume 4, Advances in Intelligent Systems and Computing, Springer, 2023.
  • ● Y. Furusho and K. Ikeda, "Theoretical Analysis of ResNet and Batch Normalization from Generalization and Optimization Perspectives", APSIPA Transactions on Signal and Information Processing, 2020.
  • ● Y. Furusho, T. Kubo, and K. Ikeda, "Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective", Neurocomputing, 2017.

Patents (Issued ones only):

  • ● P7585386, " LEARNING SYSTEM, METHOD AND NON-TRANSITORY COMPUTER READABLE MEDIUM"
  • ● P7520777, " LEARNING SYSTEM”

Awards/Prizes:

  • ● SICE Academic Encouragement Award, 2020.
  • ● IEICE TC-IBISML Research Award Finalist, 2019.
  • ● Best Poster Paper Award of Artificial Intelligence Symposium, Brain Engineering Society of Korea, 2017.
  • ● Outstanding Performance Award of Student Venture Dream Challenge Business Award in Kumamoto, 2013.