IKE Yuichi

IKE Yuichi is an Associate Professor in the Graduate School of Mathematical Sciences at The University of Tokyo. His research focuses on microlocal sheaf theory, topological data analysis, and their applications to geometry and symplectic geometry. He studies the mathematical structure of persistent homology and its integration with machine learning. His work includes applications of microlocal sheaf theory to non-smooth objects in symplectic geometry. Notable publications include research on derived interleaving distances, persistent homology-based functions, and neural network layers for persistence diagrams. His research is supported by affiliations with the Graduate School of Mathematical Sciences and the Kavli IPMU.

Yuichi Ike is a researcher in the Graduate School of Mathematical Sciences at The University of Tokyo, specializing in Microlocal sheaf theory and Topological data analysis. His work explores the intersection of topology and machine learning, focusing on methods to extract meaningful information from complex data structures. Ike's research includes developing neural network layers for persistence diagrams, optimizing persistent homology-based functions, and creating topologically-oriented learning frameworks. He also investigates sheaf quantization and its applications to symplectic geometry and Lagrangian intersections. His contributions span both theoretical and applied aspects of topological data analysis, with an emphasis on enhancing interpretability and robustness in machine learning models.