2023/2/28 16:31
TrustML Young Scientist Seminar #54 20230208  Talk by Zhen Fang (University of Technology Sydney) サムネイル

説明

The 54th Seminar
Date and Time: February 8th 2:00 pm – 3:00 pm(JST)
Venue: Zoom webinar
Language: English

Speaker: Zhen Fang (University of Technology Sydney)
Title: Understanding Generalized Out-of-Distribution Detection: A Theoretical View
Short Abstract:
Out-of-distribution (OOD) detection is vital to ensuring the safety and reliability of artificial intelligence systems. It is a novel but trending area in machine learning and artificial intelligence. OOD detection was proposed in 2017 and since then has shown great potential to ensure the reliable deployment of machine learning models in the real world. In the past few years, a rich line of algorithms have been developed to empirically address the OOD detection problem. However, very few works study the fundamental principles of OOD detection, which hinders the rigorous path forward for the field. In this talk, we will introduce the novel progress related to theoretical understanding of OOD detection.

Bio:
Dr Zhen Fang is currently a Research Fellow at the Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), working with Prof. Jie Lu. He received his master degree in pure mathematics from Xiamen University (2014-2017), working with Prof. Bo Guan. He received his Ph.D degree in artificial intelligence from UTS (2018-2022), working with Prof. Jie Lu. His research interests include transfer learning, statistical learning theory and out-of-distribution learning, and his works have been published in leading journals and conferences e.g., NeurIPS, ICML and IEEE-TPAMI. Recently, Zhen also received the Outstanding Paper Award in NeurIPS 2022 for his work related to out-of-distribution learning.