活动预告 | 学术研讨会系列2

2024年5月30日 （周四）

04:30 PM - 05:15 PM

Zoom Meeting No: 98807026208

Passcode: 14277295

Dr. Zhen Fang, Lecturer, University of Technology Sydney

Dr. Zhen Fang is a lecturer at the University of Technology Sydney, Australia. He received his Ph.D. from the University of Technology Sydney in 2021, under the supervision of Prof. Jie Lu. His research focuses on the algorithmic and theoretical foundations of transfer learning and out-of-distribution learning. He has served as an Area Chair for NeurIPS and ACM MM. He is the recipient of the Australasian AI Emerging Researcher Award, the NeurIPS 2022 Outstanding Reviewer Award, and the AJCAI 2023 Outstanding Service Award. His work on out-of-distribution learning received the Outstanding Paper Award at NeurIPS 2022.

As Confucius said, “No pretending to know what you don’t actually know.” Out-of-distribution (OOD) detection aims to give AI the wisdom to embody this principle. First proposed in 2017, the concept of OOD detection has demonstrated significant potential for enabling the reliable deployment of machine learning models in real-world applications, including medical safety and autonomous driving systems. Over the past few years, a rich line of algorithms has been developed to empirically address the OOD detection problem. Recently, there have also been notable theoretical advancements in OOD detection. In this talk, I will present the latest developments in OOD detection theory. Additionally, I will introduce a new theory-driven algorithmic framework. This framework is the first to incorporate techniques from distributionally robust learning into OOD detection, paving a new way for the development of OOD detection.

2024年6月3日 （周一）

02:15 PM - 03:15 PM

MBG01, G/F, Patrick Lee Wan Keung Academic Building

Professor TSUI Kwok-Leung

Grado Department of Industrial and Systems Engineering at Virginia Polytechnic and State University

Professor TSUI Kwok-Leung is professor in the Grado Department of Industrial and Systems Engineering at Virginia Polytechnic and State University. Prior to that, Prof. Tsui was chair professor in the School of Data Science and Department of Systems Engineering and Engineering Management at City University of Hong Kong in 2009-2020; professor/associate professor in the School of Industrial and Systems Engineering at Georgia Institute of Technology in 1990-2011. Prof. TSUI received his Ph.D. in Statistics from the University of Wisconsin at Madison. He was a recipient of the National Science Foundation Young Investigator Award. He has been named on the list of Clarivate "Highly Cited Researchers 2023”, and included in the World’s Top 2% Scientists published in 2023 by Stanford University in the US. He is Fellow of the Institute for Operation Research and Management Science (INFORMS), American Statistical Association (ASA), American Society for Quality (ASQ), International Society of Engineering Asset Management, and Hong Kong Institution of Engineers; elected member and council member of International Statistical Institute (ISI); and U.S. representative to the ISO Technical Committee on Statistical Methods. Prof. Tsui was Chair of the INFORMS Section on Quality, Statistics, and Reliability and the Founding Chair of the INFORMS Society on Data Mining. His current research interests include data science and predictive analytics, surveillance in healthcare and public health, personalized health monitoring, prognostics and systems health management, calibration and validation of computer models, process control and monitoring, and robust design and Taguchi methods.

Due to the advancement of sensor technologies, data collection devices, and data analytics methods, the field of systems health monitoring and management have been evolved in the past with different names under different application domains, including statistical process control and monitoring (SPCM), healthcare and public health surveillance, prognostics and health management (PHM), engineering asset management (EAM), personalized medicine, etc. There are tremendous opportunities in interdisciplinary research on system monitoring through integration of process monitoring, system informatics, data analytics, PHM, and personalized health management, etc. In this talk we will present our views and experiences in the evolution of systems health monitoring and management, its challenges and opportunities, as well as its applications in machine systems health management and human systems health management.

2024年6月04日 （周二）

10:15 AM - 11:15 AM

SEK104, 1/F, Simon & Eleanor Kwok Building

Prof. CHEN Lunan

Professor, Executive director, Key Laboratory of Systems Biology Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences

Chair Professor of Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences

Prof. CHEN Luonan received BS degree in the Electrical Engineering from Huazhong University of Science and Technology, and the M.E. and Ph.D. degrees in the electrical engineering from Tohoku University, Sendai, Japan, respectively. From 1997, he was an associate professor of the Osaka Sangyo University, Osaka, Japan, and then a full Professor. Since 2010, he has been a professor and executive director at Key Laboratory of Systems Biology, Shanghai Institute of Biochemistry and Cell Biology, Chinese Academy of Sciences; Chair Professor of Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences. He was elected as the founding president of Computational Systems Biology Society of OR China, and Chair of Technical Committee of Systems Biology at IEEE SMC Society. In recent years, he published over 400 journal papers and four monographs (books) in the area of bioinformatics, nonlinear dynamics and machine learning, including Nature, Nature Communications, PNAS, NSR, PRL, Nature Genetics, Nature Cancer, Advanced Sciences, Cell Research.  

Prof. CHEN Luonan will present a new concept "Dynamical Data-Science" and AI for quantifying dynamical processes, disease progressions and various phenotypes, including dynamic network biomarkers (DNB) for early-warning signals of critical transitions, spatial-temporal information (STI) transformation for short-term time-series prediction, partial cross-mapping (PCM) for causal inference among variables, and further AI applications to medicine. These methods are all data-driven or model-free approaches but based on the theoretical frameworks of nonlinear dynamics. We show the principles and advantages of dynamical data-driven approaches for phenotype quantification as explicable, quantifiable, and generalizable. In particular, different from statistical data-science, dynamical data-science approaches exploit the essential features of dynamical systems in terms of data, e.g. strong fluctuations near a bifurcation point, low-dimensionality of a center manifold or an attractor, and phase-space reconstruction from a single variable by delay embedding theorem, and thus are able to provide different or additional information to the traditional approaches, i.e. statistics-based data science approaches. The dynamical data-science approaches for the quantifications of various phenotypes will further play an important role in the systematical research of various fields in biology and medicine as well as AI.

Enquiry: sds@ln.edu.hk