AI for detection and classification problems

Người báo cáo: Prof. Nguyen Tien Zung (Torus AI & University Paul Sabatier, Toulouse - France)

Thời gian: 14h chiều Thứ 5, ngày  07/05/2026

Địa điểm: Phòng  507 nhà A6

Abstract:  In this talk, I will cover the following topics:

  • Distorted probabilities: why it's good for the AI to show not mathematical but rather distorted probabilities
  • Natural loss functions: why the square loss and the log loss (cross entropy) are the two most natural loss functions, but in practice it's better to use other convex, focal loss functions, and why all convex loss functions are in a sense equivalent up to a reparametrization of probabilities Convexity of the ROC curve
  • How big is big data ? Actually whatever amount of data you have, it's still quite small, and it's more important to have "dense" data than "big" data.
  • The "unknown" class: why it's important to have it in any classifier
  • Hierarchical classification: why hierarchy matters
  • Exclusive vs inclusive classification
  • Partial annotation: data are often only partially annotated, how to deal with this problem ?
  •  Few shot and zero shot learning: how to recognize things that one has never seen before ?!
  •  Cross validation done right
  •  How to learn very rare classes ?
  Hoạt động tuần
Xuất bản mới
Trần Quang Hóa, Đỗ Trọng Hoàng, Le Van Dinh, Nguyễn Đăng Hợp, Thái Thành Nguyễn, Asymptotic depth of invariant chains of edge ideals, Journal of Combinatorial Theory, Series A Volume 224, November 2026, 106221 .
Nguyễn Duy Tân, Nguyễn Quốc Thắng, On fields with Serre's property (F) and the finitude of Galois and flat cohomology of algebraic groups over fields, Ars Mathematica Contemporanea, v. 26 (2026), No. 3 .
Tan H. Cao, Boris S. Mordukhovich, Dao Nguyen, Trang Nguyen, Nguyễn Năng Thiều, Optimal control of nonconvex sweeping processes with variable time via finite-difference approximations, Nonlinear Analysis: Hybrid Systems Volume 61, August 2026, 101755 .