Program-Specific Associate Professor
Graduate School of Informatics, Kyoto University
Email: akashi.nozomi.2a[at]kyoto-u.ac.jp
Fields: Nonlinear Dynamics, Machine Learning, Embodied Cognitive Science, Dynamical Systems, Soft Robotics, Neuromorphic Computing
, Morphological Computation
Key words: Physical Reservoir Computing, Chaos, Random Number Generation, Spintronics, Pneumatic Artificial Muscle, Passive Dynamic Walker
K. Inoue, T. Kubota, Q. H. Tran, N. Akashi, R. Terajima, T. Kabayama, J. C. Guan, K. Nakajima, Reservoir computing bootcamp—from Python/NumPy tutorial for the complete beginners to cutting-edge research topics of reservoir computing, Chaos: An Interdisciplinary Journal of Nonlinear Science 36, 023109, 2026. (Selected as Front Cover & Editor's Pick) link
J. Shen, R. Al Ajroudi, N. Akashi, T. Jo, M. Nishida, Y. Wakao, R. Sakurai, Y. Kuniyoshi, K. Nakajima, Predicting Bifurcation of Mechanical Systems Using Reservoir Computing: Case Studies on Legged Locomotion and Pneumatic Soft Actuator, Chaos: An Interdisciplinary Journal of Nonlinear Science 36 013103, 2026 link
K. J. Chu, N. Akashi, A. Yamamoto, Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics, Chaos: An Interdisciplinary Journal of Nonlinear Science 35: 093138, 2025. (Selected as Editor's Pick) link
S. Liu, N. Akashi, Q. Huang, Y. Kuniyoshi, K. Nakajima, Exploiting Chaotic Dynamics as Deep Neural Networks, Physical Review Research 7: 033031, 2025. link
Y. Imai, S. Liu, N. Akashi, K. Nakajima, Gradient-based optimization of spintronic devices, Applied Physics Letters, 126 (8): 082402, 2025. link
N. Akashi, Y. Kuniyoshi, T. Jo, M. Nishida, R. Sakurai, Y. Wakao, K. Nakajima, Embedding bifurcations into pneumatic artificial muscle, Advanced Science 11: 2304402, 2024. (Selected as Inside Front Cover)
K. Okamoto, N. Akashi, I. Obayashi, K. Nakajima, H. Kokubu, K. Senda, K. Tsuchiya, S. Aoi, Sharp changes in fractal basin of attraction in passive dynamic walking, Nonlinear Dynamics 111, 21941–21955, 2023.
N. Akashi, Y. Kuniyoshi, S. Tsunegi, T. Taniguchi, M. Nishida, R. Sakurai, Y. Wakao, K. Kawashima, K. Nakajima, A Coupled Spintronics Neuromorphic Approach for High-Performance Reservoir Computing, Advanced Intelligent Systems 4: 2200123, 2022.
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Physics-informed recurrent neural networks for soft pneumatic actuators, IEEE Robotics and Automation Letters, 7 (3) pp. 6862-6869, 2022.
N. Akashi, K. Nakajima, M. Shibayama, Y. Kuniyoshi, A mechanical true random number generator, New Journal of Physics 24: 013019, 2022.
N. Akashi, T. Yamaguchi, S. Tsunegi, T. Taniguchi, M. Nishida, R. Sakurai, Y. Wakao, K. Nakajima, Input-driven bifurcations and information processing capacity in spintronics reservoirs, Physical Review Research 2: 043303, 2020.
T. Yamaguchi, N. Akashi, K. Nakajima, H. Kubota, S. Tsunegi, T. Taniguchi, Step-like dependence of memory function on pulse width in spintronics reservoir computing, Scientific Reports 10: 19536, 2020.
T. Yamaguchi, N. Akashi, S. Tsunegi, H. Kubota, K. Nakajima, T. Taniguchi, Periodic structure of memory function in spintronics reservoir with feedback current, Physical Review Research 2: 023389, 2020.
T. Yamaguchi, N. Akashi, K. Nakajima, S. Tsunegi, H. Kubota, T. Taniguchi, Synchronization and chaos in a spin torque oscillator with a perpendicularly magnetized free layer, Physical Review B 100: 224422, 2019.
T. Taniguchi, N. Akashi, H. Notsu, M. Kimura, H. Tsukahara, K. Nakajima, Chaos in nanomagnet via feedback current, Physical Review B 100: 174425, 2019.
T. Jong, N. Akashi, T. Taniguchi, H. Notsu, K. Nakajima, Virtual reservoir acceleration for CPU and GPU: Case study for coupled spin-torque oscillator reservoir, NeurIPS 2023 Workshop on Machine Learning with New Compute Paradigms (MLNCP), 2023. arXiv
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Self-organization of physics-informed mechanisms in recurrent neural networks: a case study in pneumatic artificial muscles, Proceedings of 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), pp. 409-415, 2022.
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Physics-informed reservoir computing with autonomously switching readouts: a case study in pneumatic artificial muscle, Proceedings of 2021 International Symposium on Micro-NanoMechatronics and Human Science (MHS), pp. 1-6 (6 pages), 2021 (Best Paper Awards).
R. Sakurai, M. Nishida, H. Sakurai, Y. Wakao, N. Akashi, Y. Kuniyoshi, Y. Minami, K. Nakajima, Emulating a sensor using soft material dynamics: A reservoir computing approach to pneumatic artificial muscle, in Proceedings of 2020 3rd IEEE International Conference on Soft Robotics (RoboSoft), pp. 710-717, 2020.
N. Akashi, K. Nakajima, Y. Kuniyoshi, Unpredictable as a Dice: Analyzing Riddled Basin Structures in Passive Dynamic Walker, 2019 International Symposium on Micro-NanoMechatronics and Human Science (MHS2019), pp. 119-123 (4 pages), 2019.
K. Nakajima, H. Sawada, N. Akashi, Information Processing Using Soft Body Dynamics. In The Science of Soft Robots: Design, Materials and Information Processing (Springer Singapore), pp. 357-392, 2023.
S. Hirai, H. Mochiyama, K. Nakajima, N. Akashi, Modeling and Control of Continuum Body. In The Science of Soft Robots: Design, Materials and Information Processing (Springer Singapore), pp. 279-318, 2023.
K. Nakajima, T. Li, N. Akashi, Soft timer: dynamic clock embedded in soft body. In Robotic Systems and Autonomous Platforms: Advances in Materials and Manufacturing (Woodhead Publishing in Materials ), pp. 181-196, 2018. (peer reviewed)
S. Todaka, N. Akashi, A. Yamamoto, Exploiting combinatorial optimization algorithms as a reservoir for the traveling salesman problem, 5th Symposium on Machine Learning and Dynamical Systems & Differential Equations for Data Science 2026 (MLDS5 and DEDS 2026), 10 Feb 2026. (Poster) link
K. J. Chu, N. Akashi, A. Yamamoto, Incorporating Coupling Knowledge of Dynamical Systems into Reservoir Computing for Attractor Reconstruction, 5th Symposium on Machine Learning and Dynamical Systems & Differential Equations for Data Science 2026 (MLDS5 and DEDS 2026), 10 Feb 2026. (Poster) link
N. Akashi, T. Watanabe, M. Hara, T. Namiki, H. Kokubu, I. Tsuda, K. Nakajima, Dynamic noise cancellation and reconstructing noise-induced bifurcations by reservoir computing, 5th Symposium on Machine Learning and Dynamical Systems & Differential Equations for Data Science 2026 (MLDS5 and DEDS 2026), 11 Feb 2026. link
S. Todaka, N. Akashi, A. Yamamoto, Exploiting dynamic programming algorithm of subset sum problem as a reservoir, Differential Equations for Data Science 2025, 12 Feb 2025. link
N. Akashi, Y. Imai, S. Liu, Q. Huang, Y. Kuniyoshi, K. Nakajima, Exploiting chaos in spin-torque oscillators for machine learning, Differential Equations for Data Science 2025, 12 Feb 2025. (invited) link
N. Akashi, Deep learning framework for exploiting natural chaotic dynamics, Dynamics of multicellular systems and applications in machine learning, 23 Oct 2024. (invited) link
A. Matsuo, K. Okamoto, Y. Ambe, N. Akashi, I. Obayashi, H. Kubota, S. Aoi, Change in fractal basin of attraction due to leg mass in passive dynamic walking, The 8th International Symposium on Swarm Behavior and Bio-Inspired Robotics 2024, 18 Sep 2024. link
Y. Imai, S. Liu, N. Akashi, K. Nakajima, Gradient-based optimization of spintronic devices, Optimization of spin-torque oscillator by gradient descent, International Conference on Applied Magnetism, 17 Sep 2024. link
N. Akashi, Training Autonomous Dynamics of a Soft Body: Embedding Bifurcation Structures using Physical Reservoir Computing, Fourth Symposium on Machine Learning and Dynamical Systems, 8 Jul 2024.
N. Akashi, Embedding bifurcation structures into a robotic body using physical reservoir computing, Tateyama Dynamics Workshop 2024, 10 Mar 2024.
T. Jong, N. Akashi, T. Taniguchi, H. Notsu, K. Nakajima, Virtual reservoir acceleration for CPU and GPU: Case study for coupled spin-torque oscillator reservoir, NeurIPS 2023 Workshop on Machine Learning with New Compute Paradigms (MLNCP), 16 Dec 2023 (Poster).
N. Akashi, Y. Kuniyoshi, T. Jo, M. Nishida, R. Sakurai, Y. Wakao, K. Nakajima, Embedding bifurcation structures into a soft robotic actuator, 10th International Congresson on Industrial and Applied Mathematics (ICIAM2023), 24 Aug 2023. link
K. Okamoto, N. Akashi, I. Obayashi, H. Kokubu, K. Nakajima, K. Senda, K. Tsuchiya, S. Aoi, Sudden change in fractality of basin boundary in passive dynamic walking, The 11th International Symposium on Adaptive Motion of Animals and Machines (AMAM2023), 6 - 9 Jun 2023 (Poster).
T. Taniguchi, S. Tsunegi, T. Yamaguchi, A. Kamimaki, N. Akashi, T. Kubota, K. Nakajima, H. Notsu, M. Kimura, H. Tukahara, J. Grollier, V. Cros, K. Yakushiji, A. Fukushima, S. Yuasa, H. Kubota, Brain-Inspired Computing by Chaotic Spin-torque Oscillator, 67th Annual Conference on Magnetism and Magnetic Materials (MMM 2022), 3 Nov 2022.
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Physics-informed recurrent neural networks for soft pneumatic actuators, 2022 IEEE International Conference on Intelligent Robots and Systems (IROS), 25 Oct 2022.
N. Akashi, Y. Kuniyoshi, S. Tsunegi, T. Taniguchi, J. Takemoto, M. Nishida, R. Sakurai, Y. Wakao, K. Kawashima, K. Nakajima, Bifurcations and information-processing capability in physical reservoir computing: Case studies of pneumatic artificial muscles and spintronics devices in 82nd Workshop: Unconventional Computing: Materials, Science, Informations, Hardware, Software, 23 Oct 2022.
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Self-organization of physics-informed mechanisms in recurrent neural networks: a case study in pneumatic artificial muscles, in 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), 6 Apr 2022.
W. Sun, N. Akashi, Y. Kuniyoshi, K. Nakajima, Physics-informed reservoir computing with autonomously switching readouts: a case study in pneumatic artificial muscle, 2021 International Symposium on Micro-NanoMechatronics and Human Science (MHS2021), 7 Dec 2021.
A. Kamimaki, S. Tsunegi, T. Taniguchi, N. Akashi, K. Nakajima, A. Fukushima, S.Yuasa, V. Cros, J. Grollier and H. Kubota Physical Reservoir Computing by Spin-Torque Oscillator at the Edge of Chaos, 65th Annual Conference on Magnetism and Magnetic Materials (MMM 2020), 2 Nov 2020.
N. Akashi, T. Yamaguchi, S. Tsunegi, T. Taniguchi, M. Nishida, R. Sakurai, Y. Wakao, K. Nakajima, Input-driven bifurcations in spintronics reservoir computing, Second Symposium on Machine Learning and Dynamical Systems, 22 Sep 2020.
R. Sakurai, M. Nishida, H. Sakurai, Y. Wakao, N. Akashi, Y. Kuniyoshi, Y. Minami, K. Nakajima, Emulating a sensor using soft material dynamics: A reservoir computing approach to pneumatic artificial muscle, 2020 3rd IEEE International Conference on Soft Robotics (RoboSoft), May 2020.
N. Akashi, K. Nakajima, Y. Kuniyoshi, Unpredictable as a Dice: Analyzing Riddled Basin Structures in Passive Dynamic Walker, 2019 International Symposium on Micro-NanoMechatronics and Human Science (MHS2019), 3 Dec 2019.
T. Yamaguchi, N. Akashi, K. Nakajima, S. Tsunegi, H. Kubota and T. Taniguchi, Injection Locking of Spin-Torque Oscillator with Perpendicularly Magnetized Free Layer, 64th Annual Conference on Magnetism and Magnetic Materials (MMM 2019), 6 Nov 2019.
2025 Sep. 27th Introductory article『Incorporating coupling knowledge for learning spatiotemporally chaotic dynamics』 for our paper is published on Kudos.
https://www.growkudos.com/publications/10.1063%25252F5.0273343/reader
2025 Mar. 16th Introductory article『Optimization of spintronic device: Parameter estimation and image recognition』 for our paper is published on Kudos.
https://www.growkudos.com/publications/10.1063%25252F5.0238687/reader
The research results of Advanced Science have been press-released by Kyoto University and The University of Tokyo on 19 April 2024.
Kyoto Univ: https://www.kyoto-u.ac.jp/en/research-news/2024-04-26-0
EurekAlert!: https://www.eurekalert.org/news-releases/1042640
The research results of RoboSoft2020 have been press-released by The University of Tokyo on 15 May 2020.
https://www.u-tokyo.ac.jp/focus/en/press/z0508_00110.html
JSAI Incentive Award 2024 (June, 2025)
Young Scientist Presentation Award: The Japan Society of Applied Physics (May, 2023).
Best Paper Awards: 32th 2021 International Symposium on Micro-NanoMechatronics and Human Science (December, 2021).
Ph. D. Department of Mechano-Informatics, Graduate School of Information Science and Technology
The University of Tokyo, 2022.
M. S. Department of Applied Analysis and Complex Dynamical Systems, Graduate School of Informatics
Kyoto University, 2017.
B. S. Department of Information and computer science, School of Engineering Science
Osaka University, 2015.
RC bootcamp is an educational material for beginners of reservoir computing. It is packed with content ranging from the basics of Python to cutting-edge research in reservoir computing.
https://rc-bootcamp.github.io
github: https://github.com/rc-bootcamp/rc_bootcamp
Paper
K. Inoue, T. Kubota, Q. H. Tran, N. Akashi, R. Terajima, T. Kabayama, J. C. Guan, K. Nakajima, Reservoir computing bootcamp—from Python/NumPy tutorial for the complete beginners to cutting-edge research topics of reservoir computing, Chaos: An Interdisciplinary Journal of Nonlinear Science 36, 023109, 2026. link
リザバー計算による雑音誘起現象の予測・制御の数理
助成機関: 日本学術振興会
研究種目: 基盤研究(B)
課題番号: 25K00011
研究分担者: 渡邉天鵬, 津田一郎
研究期間: 2025年4月 - 2030年3月
物理リザバーを用いた予測と制御における具体的手法の提案及び、期待される成果の明確化
助成機関: 科学技術振興機構
研究種目: さきがけ 『未来数理科学』領域 特定課題調査
課題番号: JPMJPR24KF
研究期間: 2024年10月 - 2025年3月
リミットサイクルによる物理レザバー計算の力学系解析
助成機関: 日本学術振興会
研究種目: 特別研究奨励費
課題番号: 22KJ1786
研究期間: 2022年4月 - 2025年3月
Transformerの演繹推論能力の解明と説明可能なAIへの応用
助成機関: 日本学術振興会
研究種目: 基盤研究(A)
課題番号: 25H01112
研究代表者: 山本 章博
研究期間: 2025年4月 - 2030年3月