Deep Anomaly Detection
Data intelligence, derived from extensive learning of real-world data, has brought about substantial impact and value across multiple domains through its diverse applications. In this talk, our focus will be on the crucial task of anomaly detection, which involves identifying unusual patterns within datasets. Specifically, we will delve into the foundational concept of anomaly detection, explore its various real-world scenarios, and address the associated technical challenges. Additionally, we will examine several recent studies on deep anomaly detection techniques specifically designed for tabular, text, and time-series data.
Dongha Lee is an Assistant Professor in the Department of Artificial Intelligence at Yonsei University. He received his Ph.D. degree in Computer Science and Engineering from POSTECH and went on to work as a Postdoctoral Research Fellow at UIUC. Dr. Lee’s research focuses on knowledge mining from real-world data, as well as text mining and natural language processing (NLP) applications.