TANAKA Gouhei

写真a

Affiliation Department

工学専攻 情報工学系プログラム知能情報分野

Homepage

https://dyn.web.nitech.ac.jp/en/

External Link

Degree

  • Doctor (Science) ( 2005.03   The University of Tokyo )

Research Interests

  • Dynamical systems

  • Control

  • Bifurcation theory

  • Artificial intelligence

  • Reservoir computing

display all >>

Research Areas

  • Informatics / Soft computing

  • Informatics / Mathematical informatics

From School

  • The University of Tokyo   Graduate School of Frontier Sciences   Department of Complexity Science and Engineering, Doctoral course   Graduated

    2002.04 - 2005.03

      More details

  • The University of Tokyo   Graduate School of Frontier Sciences   Department of Complexity Science and Engineering, Master course   Graduated

    2000.04 - 2002.03

      More details

  • The University of Tokyo   Faculty of Engineering   Department of Mathematical Engineering and Information Physics   Graduated

    1998.04 - 2000.03

      More details

  • The University of Tokyo   Faculty of Liberal Arts   Natural Sciences 1   Graduated

    1996.04 - 1998.03

      More details

From Graduate School

  • The University of Tokyo   Graduate School of Frontier Sciences   Department of Complexity Science and Engineering   Doctor's Course   Completed

    - 2005.03

  • The University of Tokyo   Graduate School of Frontier Sciences   Department of Complexity Science and Engineering   Master's Course   Completed

    - 2002.03

External Career

  • Nagoya Institute of Technology   Professor

    2023.04

  • MEXT   Superrobust Computation Project, Information Science and Technology Strategic Core   Research Assistant

    2002.12 - 2005.03

  • The University of Tokyo   Institute of Industrial Science   Assistant Professor

    2007.04 - 2011.07

  • The University of Tokyo   Institute of Industrial Science   Project Associate Professor

    2011.08 - 2013.03

  • The University of Tokyo   Institute of Industrial Science   Assistant Professor

    2006.08 - 2007.03

display all >>

 

Papers

  • Long-time-constant leaky-integrating oxygen-vacancy drift-diffusion FET for human-interactive spiking reservoir computing. Reviewed

    Hisashi Inoue, Hiroto Tamura, Ai Kitoh, Xiangyu Chen, Zolboo Byambadorj, Takeaki Yajima, Yasushi Hotta, Tetsuya Iizuka, Gouhei Tanaka, Isao H. Inoue

    2023 IEEE Symposium on VLSI Technology and Circuits   1 - 2   2023.07

     More details

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

    DOI: 10.23919/VLSITechnologyandCir57934.2023.10185412

    researchmap

    Other Link: https://ieeexplore.ieee.org/document/10185412

  • Performance Enhancement of a Spin-Wave-Based Reservoir Computing System Utilizing Different Physical Conditions Reviewed

    Ryosho Nakane, Akira Hirose, Gouhei Tanaka

    Physical Review Applied   19 ( 3 )   2023.03

     More details

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

    We numerically study how to enhance reservoir computing performance by thoroughly extracting the spin-wave device potential for higher-dimensional information generation. The reservoir device has a 1-input exciter and 120-output detectors on the top of a continuous magnetic garnet film for spin-wave transmission. For various nonlinear and fading-memory dynamic phenomena distributing in the film space, small in-plane magnetic fields are used to prepare stripe domain structures and various damping constants at the film sides and bottom are explored. The ferromagnetic resonant frequency and relaxation time of spin precession clearly characterizes the change in spin dynamics with the magnetic field and damping constant. The common input signal for reservoir computing is a 1-GHz cosine wave with random 6-valued amplitude modulation. A basic 120-dimensional reservoir output vector is obtained from time-series signals at the 120-output detectors under each of three magnetic field conditions. Then, 240- and 360-dimensional reservoir output vectors are also constructed by concatenating two and three basic ones, respectively. In nonlinear autoregressive moving average (NARMA) prediction tasks, the computational performance is enhanced as the dimension of the reservoir output vector becomes higher and a significantly low prediction error is achieved for the tenth-order NARMA task using the 360-dimensional vector and optimum damping constant. The results are clear evidence that the collection of diverse output signals efficiently increases the dimensionality of the integrated reservoir state vector (i.e. reservoir-state richness) and thereby contributes to high computational performance. This paper demonstrates that performance enhancement through various configuration settings is a practical approach for on-chip reservoir computing devices with small numbers of real output nodes.

    DOI: 10.1103/PhysRevApplied.19.034047

    Scopus

    researchmap

  • Multi-Reservoir Echo State Networks with Hodrick-Prescott Filter for nonlinear time-series prediction.

    Ziqiang Li, Yun Liu, Gouhei Tanaka

    Applied Soft Computing   135   110021 - 110021   2023.03

     More details

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

    DOI: 10.1016/j.asoc.2023.110021

    researchmap

  • Spatially Arranged Sparse Recurrent Neural Networks for Energy Efficient Associative Memory. Reviewed International journal

    Gouhei Tanaka, Ryosho Nakane, Tomoya Takeuchi, Toshiyuki Yamane, Daiju Nakano, Yasunao Katayama, Akira Hirose

    IEEE transactions on neural networks and learning systems   31 ( 1 )   24 - 38   2020.01

     More details

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

    The development of hardware neural networks, including neuromorphic hardware, has been accelerated over the past few years. However, it is challenging to operate very large-scale neural networks with low-power hardware devices, partly due to signal transmissions through a massive number of interconnections. Our aim is to deal with the issue of communication cost from an algorithmic viewpoint and study learning algorithms for energy-efficient information processing. Here, we consider two approaches to finding spatially arranged sparse recurrent neural networks with the high cost-performance ratio for associative memory. In the first approach following classical methods, we focus on sparse modular network structures inspired by biological brain networks and examine their storage capacity under an iterative learning rule. We show that incorporating long-range intermodule connections into purely modular networks can enhance the cost-performance ratio. In the second approach, we formulate for the first time an optimization problem where the network sparsity is maximized under the constraints imposed by a pattern embedding condition. We show that there is a tradeoff between the interconnection cost and the computational performance in the optimized networks. We demonstrate that the optimized networks can achieve a better cost-performance ratio compared with those considered in the first approach. We show the effectiveness of the optimization approach mainly using binary patterns and apply it also to gray-scale image restoration. Our results suggest that the presented approaches are useful in seeking more sparse and less costly connectivity of neural networks for the enhancement of energy efficiency in hardware neural networks.

    DOI: 10.1109/TNNLS.2019.2899344

    Scopus

    PubMed

    researchmap

    Other Link: https://dblp.uni-trier.de/db/journals/tnn/tnn31.html#TanakaNTYNKH20

  • Recent advances in physical reservoir computing: A review Reviewed International journal

    Gouhei Tanaka, Toshiyuki Yamane, Jean Benoit Heroux, Ryosho Nakane, Naoki Kanazawa, Seiji Takeda, Hidetoshi Numata, Daiju Nakano, Akira Hirose

    NEURAL NETWORKS   115   100 - 123   2019.07

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:PERGAMON-ELSEVIER SCIENCE LTD  

    Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.

    DOI: 10.1016/j.neunet.2019.03.005

    Web of Science

    PubMed

    researchmap

    Other Link: https://dblp.uni-trier.de/db/journals/nn/nn115.html#TanakaYHNKTNNH19

  • Random and targeted interventions for epidemic control in metapopulation models. Reviewed International journal

    Gouhei Tanaka, Chiyori Urabe, Kazuyuki Aihara

    Scientific reports   4   5522 - 5522   2014.07

     More details

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

    In general, different countries and communities respond to epidemics in accordance with their own control plans and protocols. However, owing to global human migration and mobility, strategic planning for epidemic control measures through the collaboration of relevant public health administrations is gaining importance for mitigating and containing large-scale epidemics. Here, we present a framework to evaluate the effectiveness of random (non-strategic) and targeted (strategic) epidemic interventions for spatially separated patches in metapopulation models. For a random intervention, we analytically derive the critical fraction of patches that receive epidemic interventions, above which epidemics are successfully contained. The analysis shows that the heterogeneity of patch connectivity makes it difficult to contain epidemics under the random intervention. We demonstrate that, particularly in such heterogeneously connected networks, targeted interventions are considerably effective compared to the random intervention. Our framework is useful for identifying the target areas where epidemic control measures should be focused.

    DOI: 10.1038/srep05522

    Web of Science

    Scopus

    PubMed

    researchmap

  • Dynamical robustness of coupled heterogeneous oscillators. Reviewed International journal

    Gouhei Tanaka, Kai Morino, Hiroaki Daido, Kazuyuki Aihara

    Physical review. E, Statistical, nonlinear, and soft matter physics   89 ( 5 )   052906 - 052906   2014.05

     More details

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

    We study tolerance of dynamic behavior in networks of coupled heterogeneous oscillators to deterioration of the individual oscillator components. As the deterioration proceeds with reduction in dynamic behavior of the oscillators, an order parameter evaluating the level of global oscillation decreases and then vanishes at a certain critical point. We present a method to analytically derive a general formula for this critical point and an approximate formula for the order parameter in the vicinity of the critical point in networks of coupled Stuart-Landau oscillators. Using the critical point as a measure for dynamical robustness of oscillator networks, we show that the more heterogeneous the oscillator components are, the more robust the oscillatory behavior of the network is to the component deterioration. This property is confirmed also in networks of Morris-Lecar neuron models coupled through electrical synapses. Our approach could provide a useful framework for theoretically understanding the role of population heterogeneity in robustness of biological networks.

    DOI: 10.1103/PhysRevE.89.052906

    Web of Science

    Scopus

    PubMed

    researchmap

  • Dynamical robustness in complex networks: the crucial role of low-degree nodes. Reviewed International journal

    Gouhei Tanaka, Kai Morino, Kazuyuki Aihara

    Scientific reports   2   232 - 232   2012

     More details

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

    Many social, biological, and technological networks consist of a small number of highly connected components (hubs) and a very large number of loosely connected components (low-degree nodes). It has been commonly recognized that such heterogeneously connected networks are extremely vulnerable to the failure of hubs in terms of structural robustness of complex networks. However, little is known about dynamical robustness, which refers to the ability of a network to maintain its dynamical activity against local perturbations. Here we demonstrate that, in contrast to the structural fragility, the nonlinear dynamics of heterogeneously connected networks can be highly vulnerable to the failure of low-degree nodes. The crucial role of low-degree nodes results from dynamical processes where normal (active) units compensate for the failure of neighboring (inactive) units at the expense of a reduction in their own activity. Our finding highlights the significant difference between structural and dynamical robustness in complex networks.

    DOI: 10.1038/srep00232

    Web of Science

    Scopus

    PubMed

    researchmap

  • Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction. Reviewed International journal

    Gouhei Tanaka, Kazuyuki Aihara

    IEEE transactions on neural networks   20 ( 9 )   1463 - 73   2009.09

     More details

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

    A widely used complex-valued activation function for complex-valued multistate Hopfield networks is revealed to be essentially based on a multilevel step function. By replacing the multilevel step function with other multilevel characteristics, we present two alternative complex-valued activation functions. One is based on a multilevel sigmoid function, while the other on a characteristic of a multistate bifurcating neuron. Numerical experiments show that both modifications to the complex-valued activation function bring about improvements in network performance for a multistate associative memory. The advantage of the proposed networks over the complex-valued Hopfield networks with the multilevel step function is more outstanding when a complex-valued neuron represents a larger number of multivalued states. Further, the performance of the proposed networks in reconstructing noisy 256 gray-level images is demonstrated in comparison with other recent associative memories to clarify their advantages and disadvantages.

    DOI: 10.1109/TNN.2009.2025500

    Scopus

    PubMed

    researchmap

  • Bifurcation analysis on a hybrid systems model of intermittent hormonal therapy for prostate cancer Reviewed

    Gouhei Tanaka, Kunichika Tsumoto, Shigeki Tsuji, Kazuyuki Aihara

    PHYSICA D-NONLINEAR PHENOMENA   237 ( 20 )   2616 - 2627   2008.10

     More details

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

    Hybrid systems are widely used to model dynamical phenomena that are characterized by interplay between continuous dynamics and discrete events. An example of biomedical application is modeling of disease progression of prostate cancer under intermittent hormonal therapy, where continuous tumor dynamics is switched by interruption and reinstitution of medication. In the present paper, we study a hybrid systems model representing intermittent androgen suppression (IAS) therapy for advanced prostate cancer. Intermittent medication with switching between on-treatment and off-treatment periods is intended to possibly prevent a prostatic tumor from developing into a hormone-refractory state and is anticipated as a possible strategy for delaying or hopefully averting a cancer relapse which most patients undergo as a result of long-term hormonal suppression. Clinical efficacy of IAS therapy for prostate cancer is still under investigation but at least worth considering in terms of reduction of side effects and economic costs during off-treatment periods. In the model of IAS therapy, it depends on some clinically controllable parameters whether a relapse of prostate cancer occurs or not. Therefore, we examine nonlinear dynamics and bifurcation structure of the model by exploiting a numerical method to clarify bifurcation sets in the hybrid system. Our results suggest that adjustment of the normal androgen level in combination with appropriate medication scheduling could enhance the possibility of relapse prevention. Moreover, a two-dimensional piecewise-linear system reduced from the original model highlights the origin of nonlinear phenomena specific to the hybrid system. (C) 2008 Elsevier B.V. All rights reserved.

    DOI: 10.1016/j.physd.2008.03.044

    Web of Science

    researchmap

display all >>

Books and Other Publications

  • リザバーコンピューティング : 時系列パターン認識のための高速機械学習の理論とハードウェア

    田中, 剛平, 中根, 了昌, 廣瀬, 明( Role: Joint author)

    森北出版  2021.03  ( ISBN:9784627855311

     More details

    Total pages:vi, 207p   Language:jpn   Book type:Scholarly book

    researchmap

Misc

  • リザバーコンピューティング Invited

    田中剛平

    106 ( 6 )   2023.06

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)  

    J-GLOBAL

    researchmap

  • リザバーコンピューティングの概念と最近の動向

    タナカ ゴウヘイ

    電子情報通信学会誌   102 ( 2 )   108 - 113   2019.02

     More details

  • Reservoir computing utilizing spin waves: enhancement of computational performance through a practical approach for on-chip devices

    応用物理学会春季学術講演会講演予稿集(CD-ROM)   70th   2023.03

     More details

    Authorship:Last author  

    J-GLOBAL

    researchmap

  • Guest Editorial Special Issue on New Frontiers in Extremely Efficient Reservoir Computing

    Gouhei Tanaka, Claudio Gallicchio, Alessio Micheli, Juan Pablo Ortega, Akira Hirose

    IEEE Transactions on Neural Networks and Learning Systems   33 ( 6 )   2571 - 2574   2022.06

     More details

    Publishing type:Book review, literature introduction, etc.  

    DOI: 10.1109/TNNLS.2022.3172586

    Scopus

    researchmap

  • Reservoir Computing utilizing spin waves propagating through magnetic domains

    中根了昌, 廣瀬明, 田中剛平, 田中剛平, 田中剛平

    応用物理学会春季学術講演会講演予稿集(CD-ROM)   69th   2022

     More details

  • Experiments of Reconstructive Reservoir Computing to Detect Anomaly in Time-series Signals

    加藤准也, 田中剛平, 田中剛平, 中根了昌, 廣瀬明

    電子情報通信学会技術研究報告(Web)   121 ( 390(NC2021 46-78) )   2022

     More details

  • リザバー状態のマハラノビス距離を用いた省メモリ型時系列異常検知

    田村浩人, 田中剛平, 田中剛平, 藤原寛太郎

    65th   2022

     More details

  • Relationship between Computational Performance and Task Difficulty of Reinforcement Learning Methods Using Reward Machines

    渡邊隆二, 田中剛平

    電子情報通信学会技術研究報告(Web)   121 ( 444(NLP2021 126-152) )   2022

     More details

  • Effects of sparse connections in spiking neural networks for unsupervised pattern recognition

    品川大樹, 藤原寛太郎, 田中剛平, 田中剛平

    電子情報通信学会技術研究報告(Web)   121 ( 444(NLP2021 126-152) )   2022

     More details

  • Reservoir computing with spiking neural networks and reward-modulated STDP

    鶴海杭之, 田中剛平, 田中剛平

    電子情報通信学会技術研究報告(Web)   122 ( 65(NLP2022 1-25) )   2022

     More details

display all >>

Presentations

  • Diverse-Timescale Echo State Networks for Multiscale Modeling International conference

    Gouhei Tanaka

    International Conference on Neuromorphic, Natural, and Physical Computing  2023.10 

     More details

    Event date: 2023.10

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Hannover   Country:Germany  

    researchmap

  • Tailoring oxygen diffusion dynamics in three-terminal devices for spiking reservoir computing International conference

    Hisashi Inoue, H. Tamura, A. Kitoh, X. Chen, Z. Byambadorj, T. Yajima, Y. Hotta, T. Iizuka, G. Tanaka, I. H. Inoue

    MemriSys 2023  2023.11 

     More details

    Event date: 2023.11

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • リザバーコンピューティングによる時系列データ学習 Invited

    田中 剛平

    第15回Nagoyaオープンイノベーション研究会  2023.09 

     More details

    Event date: 2023.09

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • Mahalanobis Distance of Reservoir States for Highly-Efficient Time-Series Classification

    Hiroto Tamura, Kantaro Fujiwara, Kazuyuki Aihara, Gouhei Tanaka

    The 33rd Annual Meeting of the Japanese Neural Network Society  2023.09 

     More details

    Event date: 2023.09

    Language:English   Presentation type:Poster presentation  

    researchmap

  • Identity Recognition with Bidirectional Echo State Networks from Continuous Blood Pressure Data

    Ziqiang Li, Kantaro Fujiwara, Gouhei Tanaka

    The 33rd Annual Meeting of the Japanese Neural Network Society  2023.09 

     More details

    Event date: 2023.09

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • リザバーコンピューティングの高性能化・高効率化に関して Invited

    田中 剛平

    第15回 AI Optics研究グループ研究会  2023.03 

     More details

    Event date: 2023.03

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • AIによる複雑ダイナミクスのパターン認識 Invited

    田中 剛平

    日本生理学会第100回記念大会, 100周年記念事業委員会企画シンポジウム「AIが切り開く医学・生理学・生命科学の新展開」  2023.03 

     More details

    Event date: 2023.03

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • リザバーコンピューティングとマルチスケールモデリング Invited

    田中 剛平

    電子情報通信学会総合大会, チュートリアルセッション「NBT-1. 次世代ネットワークを支える数理モデルの展開」  2023.03 

     More details

    Event date: 2023.03

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • Indoor air quality prediction using multi-reservoir echo state network with attention mechanism

    Wenrui Qiu, Gouhei Tanaka

    2023.01 

     More details

    Event date: 2023.01

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • Inference of network structure in dynamic systems using a generative model International conference

    Shuhan Zheng, Gouhei Tanaka

    Dynamics Days US 2023  2023.01 

     More details

    Event date: 2023.01

    Language:English   Presentation type:Poster presentation  

    researchmap

Awards

  • Best Paper Award 3rd Prize, 29th International Conference on Artificial Neural Networks (ICANN)

    2020.11   European Neural Network Society   Two-Step FORCE Learning Algorithm for Fast Convergence in Reservoir Computing

    Hiroto Tamura, Gouhei Tanaka

     More details

  • 業績賞

    2017   日本応用数理学会   「前立腺癌の間欠的内分泌療法に関する数理的アプローチ」

    田中剛平, 合原一幸, 平田祥人, 鈴木大慈, 森野佳生

     More details

  • Best Paper Award

    2017   IEEE Transcations on Nanotechnology 2016  

    Gouhei Tanaka, Yasunao Katayama, Daiju Nakano, Toshiyuki Yamane, Ryosho Nakane

     More details

  • Best Poster Award (Silver Prize)

    2011   First International Symposium on Innovative Mathematical Modelling   Robustness of Scale-free Networks of Oscillators against Partial Inactivation

    Gouhei Tanaka

     More details

  • Honorable Mention Award, DSWeb Tutorials Contest

    2005   Society for Industrial and Applied Mathematics   Crisis-induced Intermittency in Coupled Chaotic Maps

    Gouhei Tanaka

     More details

 

Committee Memberships

  • Information-technology Promotion Agency, MITOU program   Project Manager  

    2023.08   

      More details

    Committee type:Other

    researchmap

  • Neural Networks   Action Editor  

    2023.01   

      More details

    Committee type:Other

    researchmap

  • 日本学術振興会   先導的研究開発委員会「マテリアル・インフォマティクスによるものづくりプラットフォームの戦略的構築」  

    2016 - 2018   

      More details

    Committee type:Academic society

    researchmap

  • 科学技術振興機構   研究開発戦略センター(CRDS) 「研究開発の俯瞰報告書」(システム科学技術分野)  

    2012 - 2015   

      More details

    Committee type:Academic society

    researchmap