Horie, Masanobu

Machine Learning for Physical Simulation

A Researcher, an Engineer, and an Enjoyer

Physics
- Nonlinear System
- Complex System
Mathematics
- Differential Geometry
- Information Geometry
- Functional Analysis

M. Horie and N. Mitsume. Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions. In Neural Information Processing Systems (NeurIPS), 2022. [arXiv]
M. Horie, N. Morita, T. Hishinuma, Y. Ihara, N. Mitsume. Isometric Transformation Invariant and Equivariant Graph Convolutional Networks. In International Conference on Learning Representations (ICLR), 2021. [arXiv]

M. Horie, T. Sakurai, H. Kitahata. Experimental and theoretical approach for the clustering of globally coupled density oscillators based on phase response. Physical Review E, Vol. 93, No. 1, p. 012212, 2016.

堀江正信, 森田直樹, 井原遊, 三目直登. グラフニューラルネットワークを用いたメッシュベース数値解析の汎用的な学習. 日本計算工学会論文集, No. 1, Vol. 2020, p. 20201005, 2020.
森田直樹, 堀江正信, 須藤海. 有限要素離散化した frame field による二次元メッシュ生成. 日本機械学会論文集, Vol. 86, No. 882, p. 19-00337, 2020.

堀江正信, 井原遊, 森田直樹. 高速な最適設計のためのシミュレーションと機械学習. 計算工学, 日本計算工学会, Vol. 24, No. 4, pp. 13-16, 2019年.

Masanobu Horie. Fluid Modeling Using a Combination of Numerical Analysis and Machine Learning. Strategic Basic Research Programs (PRESTO), Japan Science and Technology Agency, Japan, October 2021 - March 2025.
Tomonori Kanno, Masanobu Horie, Yu Ihara, Naoki Morita. Development of an Automatic Hexahedral Mesher for Innovating the CAE Process. IPA Mitou advanced, Information-technology Promotion Agency, Japan, September 2017 - Feburary 2018.

(So far Japanese Only)