Seminars
February 2, 2024: Dr. Khoa D. Doan (Vin Univeristy) Toward Reliable and Practical Machine Learning Applications
While Machine Learning (ML) has rapidly transformed several domains and applications with incredible successes, there are also important areas where the progress is significantly slower. Specifically, there exists a widened complexity gap between the methods currently investigated in research and those used in practice in these areas. One reason is that many algorithms, despite achieving state-of-the-art performance in “controlled” research environments, usually ignore important efficiency and practical constraints of real-world problems. In this talk, I will discuss the research effort to bridge the gap between ML research and practice with examples in various ML domains. Finally, I will discuss various projects, including Trustworthy/Federated ML, Causal Inference, Low-resource NLP, and CV for Multi-modal Environmental Intelligence, and PhD/Research Assistant opportunities (co-advised by Prof. Heng Ji and others at UIUC).
Speaker: Dr. Khoa D. Doan, Vin Univeristy
Time: 10:00 – 10:30, Friday, February 2, 2024
Venue: Room 212 E3, 144 Xuan Thuy, Cau Giay, Hanoi
Khoa D. Doan is currently an Assistant Professor of Computer Science in the College of Engineering and Computer Science, and Environment Monitoring Lab Director at the Center for Environment Intelligence at VinUniversity. Previously, he worked as an AI Researcher at Baidu Research, USA. He received his PhD in Computer Science at Virginia Tech, and MS in Computer Science at the University of Maryland, College Park. He has extensive experience working as a software engineer, data engineer/scientist, and researcher, in various industries, from scientific centers such as NASA/UMD and advertising companies such as Criteo/Baidu to ML and data analytic startups. His research focuses on developing computational frameworks that enable existing complex machine learning models to be more suitable for practical uses in various domains such as computational advertising, computer vision, natural language processing, and healthcare. Currently, his research activities include but are not limited to, deep information retrieval and its applications, generative models, and robust and reliable machine learning, with several publications at top machine learning, data mining, and computer vision conferences such as NeurIPS, ICLR, AAAI, CVPR, ICCV, SIGIR… He is a member of the Editorial Board of the new Springer’s Discover Data journal and has served as Program Committee Chair at BUGS Workshop at NeurIPS and AI for Environmental Intelligence at IEEE CAI. He is the recipient of several high-impact projects such as LLMs for healthcare, trustworthy ML, causal ML, and NLP for indigenous languages, from funding agencies such as the Gates Foundation, Grand Challenges, Amazon, and VinUni. Besides research, he spends time engaging and advising AI technology with startups.
This seminar is jointly organized with the Department of Computer Science, the Institute for Artificial Intelligence, and the Human-Machine Interface Laboratory, VNU University of Engineering and Technology.