[Date]:2025/09/10～2025/09/12

(Up-coming) Analysis of the Representational Capacity of Neural Ordinary Differential Equations Using Real Analytic Methods and Its Application to Real Data Analysis｜2025a025

Overview

• How to hold: In-person
• Venue:   IMI Conference Room (W1-D-414), West Zone 1, Ito campus
• Main language: Japanese
• Type/Category: Grant for Young Researchers and Students-Short-term Joint Research
• Title of Research Project: Analysis of the Representational Capacity of Neural Ordinary Differential Equations Using Real Analytic Methods and Its Application to Real Data Analysis
• Principal Investigator: Naoya Hatano（Postdoctral Researcher, The University of Osaka)
• Research Period: September 10, 2025.- September 12, 2025.
• Open to the Public: September 11, 2025.
• Details of the Research Plan: https://joint2.imi.kyushu-u.ac.jp/en_research_chooses/view/2025a025/en

Program

September 10, 2025.　(Closed)

September 11, 2025.　

10:00-10:40

Naoya Hatano

Extension of the Universal Approximation Theorem for Neural Networks with ReLU Activation to Unbounded Domains

11:00-11:40

Taiki Yamada

Finite Data Approximation of Ordinary Differential Equations via Echo State Networks

13:30-14:10

Ryota Kawasumi

On the universal approximation of Neural ODEs using the Orlicz norm

14:30-15:10

Keito Akiyama

Neural Network Optimization via Csiszàr-Tsallis Entropy

15:30-16:10

Noboru Isobe

On the well-posedness of gradient descent–ascent flows for minimax problems on metric spaces

September 12, 2025.(Closed)

Registration

Advance registration is required. 
Free participation fee.
(Registration also requires Organizing Committee members and speakers.)
Registration may be closed when the number of participants reaches the maximum.

＼Please go to the following link for registration.／