Kota Sueyoshi and Takashi Matsubara, "Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models," Proc. of The IEEE/CVF Computer Vision and Pattern Recognition Conference 2024 (CVPR2024), Seattle, 19 Jun. 2024. (highlight) arXiv
Takehiro Aoshima and Takashi Matsubara, "Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model," Proc. of The IEEE/CVF Computer Vision and Pattern Recognition Conference 2023 (CVPR2023), Vancouver, Jun. 2023. linkarXiv
Takashi Matsubara and Takaharu Yaguchi, "FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities," Proc. of The Eleventh International Conference on Learning Representations (ICLR2023), Kigali, May 2023. linkarXiv
Takashi Matsubara, Kazuki Sato, Kenta Hama, Ryosuke Tachibana, and Kuniaki Uehara, "Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity," IEEE Transactions on Cybernetics, vol. 52, no. 6, pp. 5161-5173, 2022. linkarXiv
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss," Proc. of The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI2022), Virtual, Feb. 2022. (oral) linkarXiv
Takashi Matsubara, Yuto Miyatake, and Takaharu Yaguchi, "Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory," Advances in Neural Information Processing Systems 34 (NeurIPS2021), Virtual, Dec. 2021. linkarXiv
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems," Advances in Neural Information Processing Systems 34 (NeurIPS2021), Virtual, Dec. 2021. (spotlight) link
Takumi Kimura, Takashi Matsubara, and Kuniaki Uehara, "ChartPointFlow for Topology-Aware 3D Point Cloud Generation," Proc. of ACM International Conference on Multimedia (ACMMM2021), Virtual, Oct. 2021. (oral) linkarXiv
Kenta Hama, Takashi Matsubara, Kuniaki Uehara, and Jianfei Cai, "Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task," ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 17, no. 2, article no. 46, 2021. linkarXiv
Takashi Matsubara, Koki Kusano, Tetsuo Tashiro, Ken'ya Ukai, and Kuniaki Uehara, "Deep Generative Model of Individual Variability in fMRI Images of Psychiatric Patients," IEEE Transactions on Biomedical Engineering, vol. 68, no. 2, pp. 592-605, 2021. link
Takashi Matsubara, Ai Ishikawa, and Takaharu Yaguchi, "Deep Energy-Based Modeling of Discrete-Time Physics," Advances in Neural Information Processing Systems 33 (NeurIPS2020), Virtual, Dec. 2020. (oral) linkarXiv
査読付原著論文
Takahito Yoshida, Takaharu Yaguchi, and Takashi Matsubara, "Loss Function for Deep Learning to Model Dynamical Systems," IEICE Transactions on Information and Systems, vol. E107-D, no. 11, pp. 1458-1462, 2024. link
Takashi Matsubara, Yuto Miyatake, and Takaharu Yaguchi, "The Symplectic Adjoint Method: Memory-Efficient Backpropagation of Neural-Network-Based Differential Equations," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 8, pp. 10526-10538, 2024. link
Hidetaka Marumo and Takashi Matsubara, "Scale-Equivariant Convolution for Semantic Segmentation of Depth Image," Nonlinear Theory and Its Applications, IEICE, vol. 15, no. 1, pp. 36-53, 2024. link
Yu Kashihara and Takashi Matsubara, "Inverse Heat Dissipation Model for Medical Image Segmentation," IEICE Transactions on Information and Systems, vol. E106-D, no. 11, pp. 1930-1934, 2023. link
Zheng Chen, Ziwei Yang, Lingwei Zhu, Peng Gao, Takashi Matsubara, Shigehiko Kanaya, and MD Altaf-Ul-Amin, "Learning Vector Quantized Representation for Cancer Subtypes Identification," Computer Methods and Programs in Biomedicine, 107543, 2023. link
Kenta Hama, and Takashi Matsubara, "Multi-Modal Entity Alignment Using Uncertainty Quantification for Modality Importance," IEEE Access, 2023. link
西井裕亮, 宮崎淳吾, 篠崎教志, 高松哲哉, 松原崇, 平田豊, "次世代モビリティに向けた眼球運動からの集中度推定," 応用数理, インダストリアルマテリアルズ, vol. 32, no.3, pp. 31-35, 2022. link
Takashi Matsubara, Kazuki Sato, Kenta Hama, Ryosuke Tachibana, and Kuniaki Uehara, "Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity," IEEE Transactions on Cybernetics, vol. 52, no. 6, pp. 5161-5173, 2022. linkarXiv
Takumi Kimura, Takashi Matsubara, and Kuniaki Uehara, "Topology-Aware Flow-Based Point Cloud Generation," IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 11, pp. 7967-7982, 2022. link
Kazuki Sato, Satoshi Nakata, Takashi Matsubara, and Kuniaki Uehara, "Few-shot Anomaly Detection using Deep Generative Models for Grouped Data," IEICE Transactions on Information and Systems, vol.E105-D, no.2, pp.436-440, 2022. link
Rousslan Fernand Julien Dossa, Shengyi Huang, Santiago Ontañón, and Takashi Matsubara, "An Empirical Investigation of Early Stopping Optimizations in Proximal Policy Optimization," IEEE Access, vol. 9, pp. 117981-117992, 2021. link
Kenta Hama, Takashi Matsubara, Kuniaki Uehara, and Jianfei Cai, "Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task," ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 17, no. 2, article no. 46, 2021. linkarXiv
Takashi Matsubara, Koki Kusano, Tetsuo Tashiro, Ken'ya Ukai, and Kuniaki Uehara, "Deep Generative Model of Individual Variability in fMRI Images of Psychiatric Patients," IEEE Transactions on Biomedical Engineering, vol. 68, no. 2, pp. 592-605, 2021. link
Kohei Nakai, Takashi Matsubara, and Kuniaki Uehara, "Neural Architecture Search for Convolutional Neural Networks with Attention," IEICE Transactions on Information and Systems, vol. E104.D, no. 2, pp. 312-321, 2021. link
Takashi Matsubara, "Target-Oriented Deformation of Visual-Semantic Embedding Space," IEICE Transactions on Information and Systems, vol. E104.D, no. 1, pp. 24-33, 2021. linkarXiv
Rousslan Fernand Julien Dossa, Xinyu Lian, Hirokazu Nomoto, Takashi Matsubara, and Kuniaki Uehara, "Hybrid of Reinforcement and Imitation Learning for Human-Like Agents," IEICE Transactions on Information and Systems, vol. E103.D, no. 9, pp. 1960-1970, 2020. link
Kazuki Kawamura, Takashi Matsubara, and Kuniaki Uehara, "Deep State-Space Model for Noise Tolerant Skeleton-based Action Recognition," IEICE Transactions on Information and Systems, vol. E103.D, no. 6, pp. 1217-1225, 2020. link
Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara, "Data Augmentation using Random Image Cropping and Patching for Deep CNNs," IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 9, pp. 2917-2931, 2020. linkarXiv
Takashi Matsubara, "Bayesian Deep Learning: A Model-based Interpretable Approach," Nonlinear Theory and Its Applications, IEICE, vol. E11-N, no. 1, pp. 16-35, 2020 (invited). link
Kohei Shimamura, Shogo Fukushima, Akihide Koura, Fuyuki Shimojo, Masaaki Misawa, Rajiv Kalia, Aiichiro Nakano, Priya Vashishta, Takashi Matsubara, and Shigenori Tanaka, "Guidelines for Creating Artificial Neural Network Empirical Interatomic Potential from First-Principles Molecular Dynamics Data under Specific Conditions and Its Application to α-Ag2Se," Journal of Chemical Physics, vol.151, 124303, 2019. link
Makoto Naruse, Takashi Matsubara, Nicolas Chauvet, Kazutaka Kanno, Tianyu Yang, and Atsushi Uchida, "Generative adversarial network based on chaotic time series," Scientific Reports, vol. 9, Article no. 12963, 2019. link
Takashi Matsubara, Tetsuo Tashiro, and Kuniaki Uehara, "Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis," IEEE Transactions on Biomedical Engineering, vol. 66, no. 10, pp. 2768-2779, 2019. linkarXiv
Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara, "A Novel Weight-Shared Multi-Stage CNN for Scale Robustness," IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 4, pp. 1090-1101, 2019. linkarXiv
Kenya Ukai, Takashi Matsubara, and Kuniaki Uehara, "Bayesian Estimation and Model Averaging of Convolutional Neural Networks by Hypernetwork," Nonlinear Theory and Its Applications, IEICE, Vol.E10-N, No.1, 2019. link
Takashi Matsubara, Ryo Akita, and Kuniaki Uehara, "Stock Price Prediction by Deep Neural Generative Model of News Articles," IEICE Transactions on Information and Systems, Vol.E101-D, No.4, pp.901-908, 2018. link
Takashi Matsubara and Kuniaki Uehara, "Asynchronous Network of Cellular Automaton-based Neurons for Efficient Implementation of Boltzmann Machines," Nonlinear Theory and Its Applications, IEICE, vol. E9-N, No.1, pp. 24-35, 2018. link
Hiroaki Mano, Gopal Kotecha, Kenji Leibnitz, Takashi Matsubara, Aya Nakae, Nicholas Shenker, Masahiko Shibata, Valerie Voon, Wako Yoshida, Michael Lee, Toshio Yanagida, Mitsuo Kawato, Maria Joao Rosa, and Ben Seymour, "Classification and characterisation of brain network changes in chronic back pain: A multicenter study," Wellcome Open Research, vol. 3, no. 19, 2018. link
Takashi Matsubara, "Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns," Frontiers in Computational Neuroscience, 21 Nov. 2017. link
Yusuke Kataoka, Takashi Matsubara, and Kuniaki Uehara, "Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference," IEE: Information Engineering Express, vol. 3, no. 4, pp. 55-66, 2017.
Ryosuke Tachibana, Takashi Matsubara, and Kuniaki Uehara, "Auto-encoder with Adversarially Regularized Latent Variables for Semi-Supervised Learning," IEE: Information Engineering Express, vol. 3, no. 3, pp. 11-20, 2017.
Ryo Akita, Akira Yoshihara, Takashi Matsubara, and Kuniaki Uehara, "Deep Learning for Stock Prediction Using Numerical and Textual Information,"_International Journal of Computer & Information Science_, vol. 17, pp. 11-16, 2016.
Takashi Matsubara and Kuniaki Uehara, "Homeostatic Plasticity Achieved by Incorporation of Random Fluctuations and Soft-Bounded Hebbian Plasticity in Excitatory Synapses," Frontiers in Neural Circuits, vol. 10, no. 42, 2016. link
Takashi Matsubara and Hiroyuki Torikai, "An Asynchronous Recurrent Network of Cellular Automaton-based Neurons and its Reproduction of Spiking Neural Network Activities," IEEE Transactions on Neural Networks and Learning Systems, vol. 27, no. 4, pp.836-852, 2016. link
Takashi Matsubara, Hiroyuki Torikai, Tetsuya Shimokawa, Kenji Leibnitz, and Ferdinand Peper, "A Novel Double Oscillation Model for Prediction of fMRI BOLD Signals without Detrending," IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol.E98.A, no.9, pp.1924-1936, 2015. link
Takashi Matsubara and Hiroyuki Torikai, "Asynchronous Cellular Automaton-Based Neuron: Theoretical Analysis and On-FPGA Learning," IEEE Transactions on Neural Networks and Learning Systems, vol. 24, no. 5, pp. 736-748, 2013. link
Takashi Matsubara and Hiroyuki Torikai, "Bifurcation-based Synthesis of Asynchronous Cellular Automaton Based Neuron," Nonlinear Theory and Its Applications, IEICE, vol. 4, no. 1, pp. 111-126, 2013. link
Takashi Matsubara and Hiroyuki Torikai, "Neuron-Like Responses and Bifurcations of a Generalized Asynchronous Sequential Logic Spiking Neuron Model," IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E95.A, no. 8, pp. 1317-1328, 2012. link
Takashi Matsubara, Hiroyuki Torikai, and Tetsuya Hishiki, "A Generalized Rotate-and-Fire Digital Spiking Neuron Model and Its On-FPGA Learning," IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 58, no. 10, pp. 677-681, 2011. link
国際会議
Takashi Matsubara and Takaharu Yaguchi, "Number Theoretic Accelerated Learning of Physics-Informed Neural Networks," Proc. of The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI2025), Philadelphia, Feb. 2025. arXiv
Kota Sueyoshi and Takashi Matsubara, "Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models," Proc. of The IEEE/CVF Computer Vision and Pattern Recognition Conference 2024 (CVPR2024), Seattle, 19 Jun. 2024. (highlight) arXiv
Takehiro Aoshima and Takashi Matsubara, "Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model," Proc. of The IEEE/CVF Computer Vision and Pattern Recognition Conference 2023 (CVPR2023), Vancouver, Jun. 2023. linkarXiv
Takashi Matsubara and Takaharu Yaguchi, "FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities," Proc. of The Eleventh International Conference on Learning Representations (ICLR2023), Kigali, May 2023. linkarXiv
Zheng Chen, Lingwei Zhu, Haohui Jia, and Takashi Matsubara, "A Two-View EEG Representation for Brain Cognition by Composite Temporal-Spatial Contrastive Learning," Proc. of SIAM International Conference on Data Mining (SDM23), Minneapolis, Apr. 2023.
Zheng Chen, Lingwei Zhu, Ziwei Yang, and Takashi Matsubara, "Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization," Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD2022), Grenoble, Sep. 2022.
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss," Proc. of The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI2022), Virtual, Feb. 2022. (oral) linkarXiv
Takashi Matsubara, Yuto Miyatake, and Takaharu Yaguchi, "Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory," Advances in Neural Information Processing Systems 34 (NeurIPS2021), Virtual, Dec. 2021. linkarXiv
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems," Advances in Neural Information Processing Systems 34 (NeurIPS2021), Virtual, Dec. 2021. (spotlight) link
Takumi Kimura, Takashi Matsubara, and Kuniaki Uehara, "ChartPointFlow for Topology-Aware 3D Point Cloud Generation," Proc. of ACM International Conference on Multimedia (ACMMM2021), Virtual, Oct. 2021. (oral) linkarXiv
Takashi Matsubara, Ai Ishikawa, and Takaharu Yaguchi, "Deep Energy-Based Modeling of Discrete-Time Physics," Advances in Neural Information Processing Systems 33 (NeurIPS2020), Virtual, Dec. 2020. (oral) linkarXiv
Kohei Nakai, Takashi Matsubara, and Kuniaki Uehara, "Att-DARTS: Differentiable Neural Architecture Search for Attention," Proc. of The 2020 International Joint Conference on Neural Networks (IJCNN2020), Glasgow (Virtual), Jul. 2020. link
Kazuki Sato, Kenta Hama, Takashi Matsubara, and Kuniaki Uehara, "Predictable Uncertainty-Aware Unsupervised Deep Anomaly Segmentation," Proc. of The 2019 International Joint Conference on Neural Networks (IJCNN2019), Budapest, Jul. 2019. link
Koki Kusano, Tetsuo Tashiro, Takashi Matsubara, and Kuniaki Uehara, "Deep Generative State-Space Modeling of FMRI Images for Psychiatric Disorder Diagnosis," Proc. of The 2019 International Joint Conference on Neural Networks (IJCNN2019), Budapest, Jul. 2019. link
Rousslan Fernand Julien Dossa, Xinyu Lian, Hirokazu Nomoto, Takashi Matsubara, and Kuniaki Uehara, "A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning," Proc. of The 2019 International Joint Conference on Neural Networks (IJCNN2019), Budapest, Jul. 2019. link
Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara, "RICAP: Random Image Cropping and Patching Data Augmentation for Deep CNNs," Proc. of The 10th Asian Conference on Machine Learning (ACML2018), Beijing, Nov. 2018, pp. 786-798. link
Kenya Ukai, Takashi Matsubara, and Kuniaki Uehara, "Hypernetwork-based Implicit Posterior Estimation and Model Averaging of Convolutional Neural Networks," Proc. of The 10th Asian Conference on Machine Learning (ACML2018), Beijing, Nov. 2018, pp. 176-191. link
Takashi Matsubara, Tetsuo Tashiro, and Kuniaki Uehara, "Structured Deep Generative Model of FMRI Signals for Mental Disorder Diagnosis," Proc. of The 21st International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2018), Granada, Sep. 2018, pp. 258-266. link
Takashi Matsubara, Ryosuke Tachibana, and Kuniaki Uehara, "Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score," Proc. of The 2018 International Joint Conference on Neural Networks (IJCNN2018), Rio de Janeiro, Jul. 2018, pp.4067-4074. link
Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara, "Scale-Invariant Recognition by Weight-Shared CNNs in Parallel," Proc. of The 9th Asian Conference on Machine Learning (ACML 2017), Seoul, Nov. 2017. link.
Yuusuke Kataoka, Takashi Matsubara, and Kuniaki Uehara, "Automatic Manga Colorization with Color Style by Generative Adversarial Nets," Proc. of The 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2017), Kanazawa, Jun. 2017, SS2-08. link
Shohei Miyashita, Xinyu Lian, Xiao Zeng, Takashi Matsubara, and Kuniaki Uehara, "Developing Game AI Agent Behaving Like Human by Mixing Reinforcement Learning and Supervised Learning," Proc. of The 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2017), Kanazawa, Jun. 2017, SS2-07. link
Takashi Matsubara, "Spike Timing-Dependent Conduction Delay Learning Model Classifying Spatio-Temporal Spike Patterns," Proc. of The 2017 International Joint Conference on Neural Networks (IJCNN2017), Anchorage, May 2017, 164. link
Takashi Matsubara and Kuniaki Uehara, "A Novel Homeostatic Plasticity Model Realized by Random Fluctuations in Excitatory Synapses," Proc. of The 2016 International Joint Conference on Neural Networks (IJCNN2016), Vancouver, Jul. 2016, N-16352.
Ryo Akita, Akira Yoshihara, Takashi Matsubara, and Kuniaki Uehara, "Deep Learning for Stock Prediction Using Numerical and Textual Information," Proc. of the 15th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2016), Okayama, Jun. 2016, pp. 945-950. link
Ryosuke Tachibana, Takashi Matsubara, and Kuniaki Uehara, "Semi-Supervised Learning Using Adversarial Networks," Proc. of the 15th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2016), Okayama, Jun. 2016, pp. 939-944. link
Yuusuke Kataoka, Takashi Matsubara, and Kuniaki Uehara, "Image Generation Using Generative Adversarial Networks and Attention Mechanism," Proc. of the 15th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2016), Okayama, Jun. 2016, pp. 933-938. link
Takashi Matsubara, Hiroyuki Torikai, Tetsuya Shimokawa, Kenji Leibnitz, and Ferdinand Peper, "A Nonlinear Model of fMRI BOLD Signal Including the Trend Component," Proc. of The 2014 International Joint Conference on Neural Networks (IJCNN2014), Beijing, Jul. 2014, pp. 2579-2586. link
Takashi Matsubara and Hiroyuki Torikai, "A Novel Reservoir Network of Asynchronous Cellular Automaton based Neurons for MIMO Neural System Reproduction," in Proc. of The 2013 International Joint Conference on Neural Networks (IJCNN2013), 1585, Dallas, Aug. 2013, pp. 1563-1569. link
Takashi Matsubara and Hiroyuki Torikai, "A Novel Bifurcation-based Synthesis of Asynchronous Cellular Automaton Based Neuron," in Artificial Neural Networks and Machine Learning - ICANN 2012 (Proc. of International Conference on Artificial Neural Networks), ser. Lecture Notes in Computer Science, vol. 7552, Lausanne, Sep. 2012, pp. 231-238. link
Hiroyuki Torikai and Takashi Matsubara, "Asynchronous Cellular Automaton Based Modeling of Nonlinear Dynamics of Neuron," in International Conference on Theory and Application in Nonlinear Dynamics (ICAND 2012), _ser. Understanding Complex Systems_, Seattle, Aug. 2012, pp. 101-112. link
Takashi Matsubara and Hiroyuki Torikai, "A Generalized Asynchronous Digital Spiking Neuron: Theoretical Analysis and Compartmental Model," in Proc. of The 2012 International Joint Conference on Neural Networks (IJCNN2012), Brisbane, Jun. 2012, pp. 185-192. link
Takashi Matsubara and Hiroyuki Torikai, "Dynamic Response Behaviors of a Generalized Asynchronous Digital Spiking Neuron Model," in Neural Information Processing - 18th International Conference (Proc. of International Conference on Neural Information Processing), ser. Lecture Notes in Computer Science (ICONIP2011), Shanghai, vol. 7064, no. III, Nov. 2011, pp. 395-404. link
Takashi Matsubara and Hiroyuki Torikai, "A Novel Asynchronous Digital Spiking Neuron Model and its Various Neuron-like Bifurcations and Responses," in Proc. of The 2011 International Joint Conference on Neural Networks (IJCNN2011), San Jose, Aug. 2011, pp. 741-748. link
国際ワークショップ
Razmik Arman Khosrovian, Takaharu Yaguchi, and Takashi Matsubara, "Port-Hamiltonian Neural Networks for Learning Coupled Systems and Their Interactions," NeurIPS 2024 Workshop on Machine Learning and the Physical Sciences, Vancouver, 15 Dec. 2024
Yosuke Nishimoto and Takashi Matsubara, "Transformer-based Imagination with Slot Attention," NeurIPS 2024 Workshop on Compositional Learning, Vancouver, 15 Dec. 2024
Keigo Tsutsui, Phuoc Thanh Tran-Ngoc, Hirotaka Sato, and Takashi Matsubara, "Deep Dynamics Modeling of Interactions in Collective Behaviors of Insects," Proc. of 2024 International Symposium on Nonlinear Theory and Its Applications (NOLTA2024), Ha Long, 3 Dec. 2024. (Student Paper Award)
Razmik Arman Khosrovian, Takaharu Yaguchi, and Takashi Matsubara, "Learning Coupled Systems and their Connectivity Using Port-Hamiltonian Neural Networks," Proc. of CAI2024 Workshop on Scientific Machine Learning and Its Industrial Applications (SMLIA2024), Singapore, 25 Jun. 2024.link
Keigo Tsutsui, Phuoc Thanh Tran-Ngoc, Hirotaka Sato, and Takashi Matsubara, "Deep Dynamics Modeling of Interactions in Insect Group Behavior," Proc. of CAI2024 Workshop on Scientific Machine Learning and Its Industrial Applications (SMLIA2024), Singapore, 25 Jun. 2024.link
Keigo Tsutsui, Phuoc Thanh Tran-Ngoc, Hirotaka Sato, and Takashi Matsubara, "Deep-Learning-Based Time-Series Analysis of Insect Behavior," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Hidetaka Marumo and Takashi Matsubara, "Scale-Equivariant Convolution for Projection-based Point Cloud Segmentation," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Kota Sueyoshi and Takashi Matsubara, "Concept Composition by Energy-Based Model using Order Embedding," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Baige Xu, Takashi Matsubara, and Takaharu Yaguchi, "Application of the neural operator for physical simulations of GENERIC systems," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Super-resolution of numerical solutions of nonlinear elliptic equations by DeepONet," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Noa Ogawa, Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Generalization Error Analysis of Discrete Hamiltonian Neural Networks," Proc. of 2023 International Symposium on Nonlinear Theory and Its Applications (NOLTA2023), Catania, Sep. 2023.
Takashi Matsubara and Takaharu Yaguchi, "Good Lattice Accelerates Physics-Informed Neural Networks," Proc. of ICML2023 Workshop on the Synergy of Scientific and Machine Learning Modeling (SynS and ML), Honolulu, Jun. 2023.
Baige Xu, Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi, "Equivalence Class Learning for GENERIC Systems," Proc. of ICML2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems (Frontiers4LCD), Honolulu, Jun. 2023.
Yuhan Chen, Baige Xu, Takashi Matsubara, Takaharu Yaguchi, "Variational Principle and Variational Integrators for Neural Symplectic Forms," Proc. of ICML2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems (Frontiers4LCD), Honolulu, Jun. 2023.
Takahito Yoshida, Takaharu Yaguchi, and Takashi Matsubara, "On Loss Function for Deep Learning of Physical Systems," RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2023), Honolulu, Feb. 2023.
Yu Kashihara and Takashi Matsubara, "Inverse Heat Dissipation Model for Image Segmentation," RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2023), Honolulu, Feb. 2023.
Takehiro Aoshima and Takashi Matsubara, "Learning Attribute Curvilinear Coordinates for Pretrained Deep Generative Model," RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP2023), Honolulu, Feb. 2023.
Takehiro Aoshima and Takashi Matsubara, "Nonlinear and Commutative Editing in Pretrained GAN Latent Space," NeurIPS 2022 Workshop on NeurReps, New Orleans, Nov. 2022.
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Variational Integrator for Hamiltonian Neural Networks," Proc. of 2022 International Symposium on Nonlinear Theory and Its Applications (NOLTA2022), Online, Dec. 2022, A2L-D-02. (Student Paper Award)
Baige Xu, Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Learning Generic Systems Using Neural Symplectic Forms," Proc. of 2022 International Symposium on Nonlinear Theory and Its Applications (NOLTA2022), Online, Dec. 2022, A2L-D-03.
Yu Kashihara, and Takashi Matsubara, "Application of Denoising Image Restoration to Anomaly Detection," Proc. of 2022 International Symposium on Nonlinear Theory and Its Applications (NOLTA2022), Online, Dec. 2022, B2L-B-01.
Kenta Hama, and Takashi Matsubara, "Common Space Learning with Gaussian Embedding for Multi-Modal Entity Alignment," Proc. of 2022 International Symposium on Nonlinear Theory and Its Applications (NOLTA2022), Online, Dec. 2022, B3L-E-02. (Student Paper Award)
Rousslan Fernand Julien Dossa, Takashi Matsubara, "Toward Human Cognition-inspired High-Level Decision Making For Hierarchical Reinforcement Learning Agents, " ICML2022 Workshop on the Decision Awareness in Reinforcement Learning, Virtual/Maryland, Jul. 2022.
Takahito Yoshida, Takaharu Yaguchi, and Takashi Matsubara, "Imbalance-Aware Learning for Deep Physics Modeling," ICLR2022 Workshop on AI for Earth and Space Science (ai4earth), Virtual, Apr. 2022. link
Rousslan Fernand Julien Dossa and Takashi Matsubara, "Toward Human Cognition-inspired High-Level Decision Making For Hierarchical Reinforcement Learning Agents," The 2021 Nonlinear Science Workshop (NLSW2021), Virtual, Dec. 2021.
Takehiro Aoshima, Takashi Matsubara, and Takaharu Yaguchi, "Deep Discrete-Time Lagrangian Mechanics," ICLR2021 Workshop on Deep Learning for Simulation (SimDL), Virtual, May, 2021. link
Shunpei Terakawa, Takashi Matsubara, and Takaharu Yaguchi, "The Error Analysis of Numerical Integrators for Deep Neural Network Modeling of Differential Equations," NeurIPS2020 Workshop on Machine Learning and the Physical Sciences (ML4PS), Virtual, Dec. 2020. link
Boqian Zhou, Hirokazu Nomoto, Takashi Matsubara, and Kuniaki Uehara, "Training Pedestrians' Detector Based on Hybrid Loss with Weak Annotations," Proc. of The 8th Korea-Japan Joint Workshop on Complex Communication Sciences (KJCCS), Hiroshima, Jan. 2020.
Kenta Hama, Takashi Matsubara, and Kuniaki Uehara, "Image-Caption Retrieval with Evaluating Uncertainties," Proc. of The 7th Japan-Korea Joint Workshop on Complex Communication Sciences (JKCCS), Pyengonchang, Jan. 2019. (Best Paper Award)
Xiao Zeng, Takashi Matsubara, and Kuniaki Uehara, "Episode-efficient Exploration for Safe Reinforcement Learning," Proc. of The 2018 International Symposium on Nonlinear Theory and its Applications (NOLTA2018), Tarragona, Sep. 2018.
Tetsuo Tashiro, Takashi Matsubara, and Kuniaki Uehara, "Deep Neural Generative Model for fMRI Image Based Diagnosis of Mental Disorder," Proc. of The 2017 International Symposium on Nonlinear Theory and its Applications (NOLTA2017), Cancun, Dec. 2017, pp. 700-703, 5169.
Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara, "Multi-Stage Convolutional Neural Networks for Robustness to Scale Transformation," Proc. of The 2017 International Symposium on Nonlinear Theory and its Applications (NOLTA2017), Cancun, Dec. 2017, pp. 692-695, 5056.
Takashi Matsubara and Kuniaki Uehara, "Efficient Implementation of Boltzmann Machine using Asynchronous Network of Cellular Automaton-based Neurons," Proc. of The 2016 International Symposium on Nonlinear Theory and its Applications (NOLTA2016), Yugawara, Nov. 2016, pp. 634-637.
Takashi Matsubara and Kuniaki Uehara, "The STDP with Fluctuations Agrees with the Changes and the Distributions of the Synaptic Weights," in Proc. of The 2015 International Symposium on Nonlinear Theory and its Applications (NOLTA2015), Hong Kong, Dec. 2015, pp. 217-220.
Takashi Matsubara and Hiroyuki Torikai, "Long-Term Spine Volume Dynamics Corresponds Partially With Multiplicative STDP," in Proc. of The 2014 International Symposium on Nonlinear Theory and its Applications (NOLTA2014), Luzern, Sep. 2014, pp. 699-702.
Takashi Matsubara, Hiroyuki Torikai, Tetsuya Shimokawa, Kenji Leibnitz, and Ferdinand Peper, "A Nonlinear Circuit Network Toward Brain Voxel Modeling," in Proc. of The 2013 International Symposium on Nonlinear Theory and its Applications (NOLTA2013), Santa Fe, Sep. 2013, pp. 421-424.
Takashi Matsubara and Hiroyuki Torikai, "Basic Analysis of Generalized Asynchronous Digital Spiking Neuron Model," in Proc. of The 2011 International Symposium on Nonlinear Theory and its Applications (NOLTA2011), Kobe, Sep. 2011, pp. 60-63.
国際シンポジウム(査読なし)
Razmik Arman Khosrovian, Takaharu Yaguchi, and Takashi Matsubara, "Learning the Dynamics and Connectivity of Coupled Systems via Port-Hamiltonian Neural Networks," REMODEL-DSC Workshop on Machine Learning and Physics, Sapporo, 31 Aug. 2024. link
Baige Xu, Yusuke Tanaka, Takashi Matsubara, Takaharu Yaguchi, "Operator Learning of Hamiltonian Density for Modeling Nonlinear Waves," International Conference on Scientific Computation and Differential Equations (SciCADE), Singapore, 18 Jul. 2024.
Takashi Matsubara, Takaharu Yaguchi, "An error bound of PINNs for solving differential equations," International Conference on Scientific Computation and Differential Equations (SciCADE), Singapore, 15 Jul. 2024.
Yuhan Chen, Takashi Matsubara, and Takaharu Yaguchi, "Geometric Integrators for Neural Symplectic Forms," 10th International Congress on Industrial and Applied Mathematics (ICIAM2023), Tokyo, Aug. 2023.
Baige Xu, Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi, "Structure-Preserving Learning for GENERIC systems," 10th International Congress on Industrial and Applied Mathematics (ICIAM2023), Tokyo, Aug. 2023.
Taisei Ueda, Takashi Matsubara, Takaharu Yaguchi, "Application of the Kernel Method to Learning Hamiltonian Equations," 10th International Congress on Industrial and Applied Mathematics (ICIAM2023), Tokyo, Aug. 2023.
Baige Xu, Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi, "Learning GENERIC Systems Using Neural Symplectic Forms," International Conference on Scientific Computation and Differential Equations (SciCADE), Reykjavík, Jul. 2022.
Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi, "Theoretical analysis of approximation properties of Hamiltonian neural networks," International Conference on Scientific Computation and Differential Equations (SciCADE), Reykjavík, Jul. 2022.
Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi, "Neural symplectic form and coordinate-free learning of Hamiltonian dynamics," International Conference on Scientific Computation and Differential Equations (SciCADE), Reykjavík, Jul. 2022.
Kimiaki Shirahama, Takumi. Sato, Norihiro Yamawaki, Takashi Matsubara, and Kuniaki Uehara, "Kindai University and Osaka Gakuin University and Osaka University at TRECVID 2021 AVS Tasks," Proc. of TREC Video Retrieval Evaluation (TRECVID), Virtual, Nov. 2021.
Daiki Mukai, Ryosuke Utsunomiya, Shunsuke Utsuki, Kimiaki Shirahama, Takashi Matsubara, and Kuniaki Uehara, "Kindai University and Osaka Gakuin University at TRECVID 2020 AVS and ActEV Tasks," Proc. of TREC Video Retrieval Evaluation (TRECVID), Virtual, Nov. 2020.
Kimiaki Shirahama, Daichi Sakurai, Takashi Matsubara, and Kuniaki Uehara, "Kindai University and Kobe University at TRECVID 2019 AVS Task," Proc. of TREC Video Retrieval Evaluation (TRECVID), Gaithersburg, Nov. 2019.
Takashi Matsubara "Neural Generative Model of Small Dataset for Leveraging Our Knowledge," in The 2nd NTU-Kobe U Joint Workshop 2018, Data Science and Artificial Intelligence, Singapore, Mar. 2018.
Takashi Matsubara "Artificial Neural Networks with Domain-Knowledge," in The 7th Kobe University Brussels European Center Symposium, Brussels, Nov. 2016.
Takashi Matsubara and Hiroyuki Torikai, "Asynchronous Cellular Automaton Based Neuron and its Reproduction Capability of Neuron-like Responses," in Kyoto Workshop on NOLTA, Kyoto, Nov. 2011, NP07.
解説論文
Takehiro Aoshima and Takashi Matsubara, "Semantic Images Editing by Operations on Latent Space of Deep Generative Models," 日本画像学会誌, vol. 62, no. 6, pp.579-587, 2023. link
松原崇, 陳鈺涵, 谷口隆晴, "幾何学的深層学習による力学系のグレーボックスモデル化," 人工知能, vol. 38, no. 3, pp. 308-317, 2023. link
松原崇, "ニューラルネットワークが近似する関数の性質と応用," 日本神経回路学会誌, vol. 25, no. 4, pp. 175-180, 2018. link
松原崇, "敵対的生成ネットワークとその応用," 映像情報メディア学会誌, 9月号, 2018.
松原崇, "深層学習は何をどのように"学習"するのか," 科学哲学, vol. 50 (合併号), 2017. link
松原崇, "fMRIで計測されたBOLD信号の線形・非線形モデル," 日本神経回路学会誌, vol. 21, no. 2, pp. 87-92, 2014. link
著書
松原崇, "ニューラル常微分方程式とその周辺," in 数理科学 2024年4月号 No.730 データサイエンスと数理モデル , サイエンス社, 2024. link
青嶋雄大, 松原崇, "潜在空間で画像編集―大きさ・色・形,思いどおりに画像を編集!," in コンピュータビジョン最前線 Winter 2023, 共立出版, 2023. link
松原崇, "データの持つ複雑さに堅牢な異常検知技術," in データ分析の進め方及びAI・機械学習導入の指南 ~データ収集・前処理・分析・評価結果の実務レベル対応~, 情報機構, 2020. link
Takashi Matsubara and Hiroyuki Torikai, "Hardware-oriented neuron modeling approach by reconfigurable asynchronous cellular automaton", in Mathematical Approaches to Biological Systems: Networks, Oscillations and Collective Motions, Springer (ed. T. Ohira), 2015, pp. 55-75. link
招待講演
松原崇, "物理法則を発見・保証する深層科学技術計算," 産応協対話交流会セミナー, 大阪, 6月, 2024. link
Takashi Matsubara, "Deep Learning Meets Geometric Mechanics," CAI 2024 Workshop on Scientific Machine Learning and Its Industrial Applications (SMLIA2024), Singapore, Jun. 2024. link
Takashi Matsubara, "Deep Geometric Mechanics: From Hamiltonian Neural Networks to Discrete-Time Physics and Beyond," International Conference on Scientific Computing and Machine Learning (SCML), Kyoto, Mar. 2024. link
松原崇, "微分方程式の数値解法に学ぶ・使う・代わる深層学習," 数値解析セミナー(UTNAS), 東京, 1月, 2024. link
松原崇, "計算機シミュレーションのための幾何学的深層学習," STEシミュレーション研究会:計算科学とデータ科学の融合に向けて, 神戸, Dec. 2023. link
Takashi Matsubara, "Geometric Deep Learning for Modeling Dynamical Systems and Incorporating Laws of Physics," Tutorial 02 New Trends in Machine Learning for Science and Engineering at 2023 SICE Annual Conference (SICE), Tsu, Sep. 2023. link
Takehiro Aoshima and Takashi Matsubara, "Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model," 第26回 画像の認識・理解シンポジウム (MIRU2023), 浜松, 7月, 2023.
Takashi Matsubara, "Geometric and Bayesian Deep Learning for Incorporating Our Needs," Japanese-Canadian Frontiers of Science (JCFoS) Symposium, Mar. 2023. link
Takashi Matsubara, Yuhan Chen, Takaharu Yaguchi (speaker), "Geometric Deep Energy-Based Models for Physics", Workshop on Functional Inference and Machine Intelligence (FIMI2022), Mar. 2022.
松原崇, "データの性質や物理法則を保証する幾何学的深層学習," 電子情報通信学会 情報論的学習理論と機械学習研究会 (IBISML), オンライン, 3月, 2022. link
松原崇, "階層的深層学習による異環境データ統合技術," ICTイノベーションフォーラム2021, オンライン, 2月, 2022. link
Takashi Matsubara, "Deep Learning Regularized by Structure and Hierarchy," Proc. of The 7th Japan-Korea Joint Workshop on Complex Communication Sciences (JKCCS), Pyengonchang, Jan. 2019.
Lian Xinyu, Rousslan Fernand Julien Dossa, Hirokazu Nomoto, Takashi Matsubara, Kuniaki Uehara, "A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning," 電子情報通信学会技術研究報告 複雑コミュニケーションサイエンス研究会 (CCS), vol. 118, no. 316, CCS2018-41, pp. 45-50, 神戸, 11月, 2018.
Long Niu, Seiji Sakakibara, Seiki Tokunaga, Sachio Saiki, Takashi Matsubara, Masahide Nakamura, Kuniaki Uehara, "Reasoning daily activities of single life using environment sensing and indoor location," 電子情報通信学会技術研究報告 情報ネットワーク研究会, vol. 116, no. 251, IN2016-49, pp. 7-8, 大阪, 10月, 2016.
Takashi Matsubara, Kenji Leibnitz, Hiroaki Mano, Takashi Shinozaki, Tetsuya Shimokawa, and Ben Seymour, "Analyzing Functional Brain Big Data: Opportunities for AI!," The 6th CiNet General Conference, Minabe, Oct. 2016, 27.
Takashi Matsubara, Hiromasa Takemura, and Ferdinand Peper, "What can AI Learn from White Matter Plasticity," The 6th CiNet General Conference, Minabe, Oct. 2016, 25.
Hiroyuki Torikai, Takashi Matsubara, and Takuya Noguchi, "Asynchronous Sequential Logic Neuron Models: Concepts, Proofs of Concepts, and Potential Applications," Proc. of The 2012 IEEE Workshop on Nonlinear Circuit Networks, pp. 76-78, Tokushima, Dec. 2012.
Takashi Matsubara and Hiroyuki Torikai, "Asynchronous Cellular Automaton Based Neuron and its Reproduction Ability," Proc. of The 2012 IEEE Workshop on Nonlinear Circuit Networks, pp. 31-32, Tokushima, Dec. 2012.
Takashi Matsubara and Hiroyuki Torikai, "Responses of Asynchronous Cellular Automaton Based Neuron Model -Toward realization of an FPGA Hippocampus-," 電子情報通信学会技術研究報告 複雑コミュニケーションサイエンス研究会 (CCS), CCS-2011-042, pp. 205-210, 東京, 3月 2012.
Takashi Matsubara and Hiroyuki Torikai, "Artificial Neuron Model by using Self-Reconfigurable Asynchronous Sequential Logic," 電子情報通信学会技術研究報告 複雑コミュニケーションサイエンス研究会 (CCS), CCS-2011-031, pp. 62--67, 沖縄, 11月 2011.
松原崇, 鳥飼弘幸, "一般化非同期デジタルスパイクニューロンモデルの興奮特性 - Field programmable neuron arrayの構築に向けて," 電子情報通信学会技術研究報告 ニューロコンピューティング研究会(NC), vol. 110, no. 38, pp. 129-134, 札幌, 1月 2011.