Title: Model-Independent Explainable AI
Speaker: Mr. Yuya Yoshikawa (Senior Researcher, Artificial Intelligence and Software Technology Research Center (STAIR Lab), Chiba Institute of Technology)
Abstract: Explainable AI (XAI) is a technology that provides human-understandable explanations for the outputs of black-box AI models. When explaining non-differentiable models or models provided as Software-as-a-Service (SaaS), it is common to use model-agnostic explanation methods that infer reasons from the model’s inputs and outputs. This presentation introduces representative model-agnostic explanation methods that are particularly suitable for XAI. We then explain a model-agnostic explanation method we researched, which enables efficient explanation generation by leveraging the nested structure of the input.
- Date
-
21st November, 2025（Fri,）18:00～20:00
- Venue
-
Held online
- Organizer
-
Co-organizer (HRAM The Japan Society for Industrial and Applied Mathematics, D-DRIVE National Network)
- Participation Fee
-
Free（Advance registration required）
https://www-mmds.sigmath.es.osaka-u.ac.jp/structure/activity/ai_data.php?id=103
- web
-
https://www-mmds.sigmath.es.osaka-u.ac.jp/structure/activity/ai_data.php?id=103
- Contact
-
Takashi Suzuki
suzuki@sigmath.es.osaka-u.ac.jp