業績

【論文誌 (査読あり)】Yudai Ebato, Sou Nobukawa, Yusuke Sakemi, Haruhiko Nishimura, Takashi Kanamaru, Nina Sviridova, Kazuyuki Aihara, "Impact of time-history terms on reservoir dynamics and prediction accuracy in echo state networks", Scientific Reports 14:8631 (2024) Link

【論文誌 (査読あり)】Yusuke Sakemi, Sou Nobukawa, Toshitaka Matsuki, Takashi Morie, Kazuyuki Aihara, "Learning reservoir dynamics with temporal self-modulation", Communications Physics 7, 29 (2024) Link

【論文誌 (査読あり)】Sou Nobukawa, Takashi Ikeda, Mitsuru Kikuchi, Tetsuya Takahashi, "Atypical instantaneous spatio‑temporal patterns of neural dynamics inAlzheimer’s disease", Scientific Reports 14:88 (2024) Link  

【論文誌 (査読なし)】Yudai Ebato, Sou Nobukawa, Yusuke Sakemi et al. Impact of Time-History Terms on Reservoir Dynamics and Prediction Accuracy in Echo State Networks, 08 January 2024, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-3834443/v1]

【論文誌 (査読あり)】Yusuke Sakemi, Kakei Yamamoto, Takeo Hosomi, Kazuyuki Aihara, "Sparse-firing regularization methods for spiking neural networks with time-to-first spike coding", Scientific Reports 13:22897 (2023) Link  

【国際学会 (査読あり)】I.Matsumoto, S. Nobukawa, T. Kurikawa, N. Wagatsuma, Y. Sakemi, T. Kanamaru, N. Sviridova, K. Aihara, "Optimal Excitatory and Inhibitory Balance for High Learning Performance in Spiking Neural Networks with Long-Tailed Synaptic Weight Distributions", International Joint Conference on Neural Networks (IJCNN), DOI: 10.1109/IJCNN54540.2023.10191709 (2023) Link 

【論文誌 (査読なし)】Kakei Yamamoto, Yusuke Sakemi, Kazuyuki Aihara, "Timing-Based Backpropagation in Spiking Neural Networks Without Single-Spike Restrictions", arXiv: 2211.16113 (2022) Link  Scholar

【論文誌 (査読あり)】Osamu Nomura, Yusuke Sakemi, Takeo Hosomi, and Takashi Morie, "Robustness of Spiking Neural Networks based on Time-To-First-Spike Encoding against Adversarial Attacks",  IEEE Transactions on Circuits and Systems-II: Express Briefs, Vol. 69, 9, 3640-3644 (2022) Link  Scholar 

【国際学会 (査読あり)】 Yusuke Sakemi, Kai Morino, Takashi Morie, Takeo Hosomi, and Kazuyuki Aihara,  "A Spiking Neural Network with Resistively Coupled Synapses Using Time-to-First-Spike Coding Towards Efficient Charge-Domain Computing" International Symposium on Circuits and Systems (ISCAS), pp. 2152-2156 (2022) Link Scholar

【論文誌 (査読あり)】Seiji Uenohara and Kazuyuki Aihara, " A 18.7 TOPS/W Mixed-Signal Spiking Neural Network Processor With 8-bit Synaptic Weight On-Chip Learning That Operates in the Continuous-Time Domain, " IEEE Access, Vol.10, pp.48338-48348 (2022) Link  Scholar 

【論文誌 (査読あり)】K. Aihara, R. Liu, K. Koizumi, X. Liu, and L. Chen: "Dynamical Network Biomarkers: Theory and Application," Gene, Vol.808, Article No.145997, pp.1-10 (2022) Link   Scholar 

【論文誌 (査読あり)】Timothée Leleu, Farad Khoyratee, Timothée Levi, Ryan Hamerly, Takashi Kohno, and Kazuyuki Aihara, " Scaling Advantage of Chaotic Amplitude Control for High-performance Combinatorial Optimization," Communications Physics, Vol.4, Article No.266, pp.1-10 (2021) Link  Scholar 

【論文誌 (査読あり)】Yusuke Sakemi, Kai Morino, Takashi Morie, and Kazuyuki Aihara, "A Supervised Learning Algorithm for Multilayer Spiking Neural Networks Based on Temporal Coding Toward Energy-Efficient VLSI Processor Design", IEEE Transactions on Neural Networks and Learning Systems, Vol. 34, pp. 394-408 (2023)  Link   Scholar 

2023年 - 現在: 科研費 基盤研究C (非線形物理モデル融合型データ駆動手法を用いた次世代低温重力波望遠鏡の熱雑音低減) (分担者: 酒見) Link

2022年 - 現在: JSTさきがけ (研究領域: 信頼されるＡＩの基盤技術、研究課題: 脳型アナログ演算を支える数理モデリング [JPMJPR22C5]) (代表: 酒見) Link

2022年 - 現在: 日本電気株式会社 共同研究「脳型コンピューティング」(代表: 酒見)

2022年 - 現在:  セコム科学技術財団 特定領域研究助成 先端数理分野 「エッジ領域で運用可能な高精度・高エネルギー効率を実現する予測モデルの構築」(代表: 酒見) Link