И.Ю. Тюкин. The challenge of building stable, accurate and robust data-driven AI

Семинар «Математические основы искусственного интеллекта» И.Ю. Тюкин. The challenge of building stable, accurate and robust data-driven AI 25 сентября 2024 г. 17:00, г. Москва, МИАН, ул. Губкина, д. 8, конференц-зал, 9 этаж Zoom Аннотация: In this talk, we will delve into the theoretical limitations of determining the guaranteed stability and accuracy of neural networks built from empirical data in classification tasks. We will show that there is a large family of tasks and settings in which computing and verifying stability and accuracy is extremely challenging. We will also discuss an intriguing connection of these results with adversarial data and examples and propose a potential way to remedy the issues by enabling the networks to adapt over time.