Prof. Wei Lu
University of Michigan, USA
Fellow of ASME
Wei Lu is a Full Professor at the Department of Mechanical Engineering, University of Michigan-Ann Arbor. He received his B.S. from Tsinghua University and a Ph.D. from Princeton University. Prof. Lu uses machine learning to address major challenges in energy and other applications. He has more than 180 journal publications in high impact peer-reviewed journals and 200 presentations and invited talks in international conferences, universities and national labs including Harvard, MIT and Stanford. He also has plenty of publications in conference proceedings, encyclopedias and book chapters. Prof. Lu was the recipient of many awards including the CAREER award by the US National Science Foundation; the Robert J. McGrattan Award by the American Society of Mechanical Engineers; Elected Fellow of the American Society of Mechanical Engineers; Robert M. Caddell Memorial Research Achievement Award; Faculty Recognition Award; Department Achievement Award; Novelis/CoE Distinguished Professor Award; CoE Ted Kennedy Family Faculty Team Excellence Award; CoE Creative, Innovative, Daring Award; CoE George J. Huebner, Jr. Research Excellence Award; and the Gustus L Larson Memorial Award by American Society of Mechanical Engineers. He was recognized as academics in the top 2% in the discipline of energy (a study from Stanford University science-wide author databases of standardized citation indicators and top 2% is the highest in the study). He was invited to the National Academies Keck Futures Initiative Conference multiple times.
Title:Integrating Machine Learning with Human Knowledge
Abstract: Machine learning has been heavily researched and widely used in
many disciplines. However, achieving high accuracy requires a large amount
of data that is sometimes difficult, expensive, or impractical to obtain.
Integrating human knowledge into machine learning can significantly reduce
data requirement, increase reliability and robustness of machine learning,
and build explainable machine learning systems. This allows leveraging the
vast amount of human knowledge and capability of machine learning to achieve
functions and performance not available before and will facilitate the
interaction between human beings and machine learning systems, making
machine learning decisions understandable to humans. In this talk I will
present some of our work in these areas, including self-directed online
machine learning for topology optimization [1], which reduced the
computational time by 5 orders of magnitude and outperformed all
state-of-the-art algorithms tested, enabling design optimizations not
possible before, integrating machine learning with human knowledge [2],
machine learning toward advanced energy storage devices and systems [3], and
application of machine learning for medical applications.
1. C. Deng, Y. Wang, C. Qin, Y. Fu, and W. Lu, “Self-directed online machine
learning for topology optimization,” Nature Communications, 13, 388, 2022.
2. C. Deng, X. Ji, C. Rainey, J. Zhang, and W. Lu, “Integrating machine
learning with human knowledge,” iScience, 23, 101656, 2020.
3. T. Gao and W. Lu, “Machine learning toward advanced energy storage
devices and systems,” iScience, 24, 101936, 2021.
Prof. Dazi Li
Beijing University of Chemical Technology, China
Li Dazi is a Full Professor and the Vice Dean of the
College of Information Science and Technology, Beijing University of
Chemical Technology. She went to Japan to study abroad in 2000 and received
the Ph.D. degree in engineering from the Department of Electrical and
Electronic Systems, Kyushu University, Fukuoka, Japan, in 2004. She is also
the head of the national first-class undergraduate program "Automation" and
a renowned teaching teacher in Beijing. Her research interests include
machine learning and artificial intelligence, advanced process control,
fault diagnosis, complex system modeling and optimization. She is currently
an Associate Editor of ISA Transactions.
Title: Graph Network based Deep Reinforcement Learning Methods for
Complex System
ABSTRACT: Nowadays,
the process industries are becoming more and more
complex, which brings challenges for data-driven real time intelligent
decision-making. Reinforcement learning based method incorporating both
prior knowledge and data-driven method is explored. Starting from graph
representation of complex process, knowledge expression & extraction
technology is studied based on reinforcement learning and graph neural
network for application in industries field. The constructed knowledge
automation system can organically integrate industrial data and expert
experience, and realize the domain knowledge extraction and reconstruction
for complex process industry driven by both prior knowledge and data. The
proposed approaches for these problems can not only contribute to the
theoretical support for deep graph reinforcement learning and its
applications, but also provide an effective new solution for the intelligent
transformation and applications in other domains under the goals of
energy-saving and efficiency-enhancing.
Prof. Wei Fang,
Jiangnan University, China
Wei Fang is a Professor at the Department of Artificial
Intelligence and Computer Science, Jiangnan University. His main research
interests include swarm intelligence and evolutionary computing. In recent
years, he has worked on the Neural Architecture Search (NAS), Pattern
Mining, and Bayesian Network Structure Learning (BNSL) based on Evolutionary
Algorithms. He has published more than 60 top journal and conference papers,
including IEEE TPAMI、TEVC、TKDE、TCYB、CIM、TSMC、TII、Information
Fusion、Information Sciences、KBS、ICDE、GECCO, etc. His Google Scholar
citations is 3909 and h-index is 33. He was the principal investigator of
projects granted from the National Natural Science Foundation of China,
National Natural Science Foundation of Jiangsu Province, China Postdoctoral
Science Foundation, etc. He is the editorial member of International Journal
of Swarm Intelligence Research, International Journal of Computing Science
and Mathematics, and Complex System Modeling and Simulation.
Title: Bayesian Network Structure Learning from Data based on Evolutionary
Algorithm with Mutual Information and Structural Information
Abstract: Bayesian Network (BN) is a probability graph model that combines
graph and probability theory and can express the causal relationship between
variables clearly. It has played an essential role in representing and
reasoning uncertain relationships, such as artificial intelligence, medical
treatment, fault diagnosis, data mining, and other fields. BN learning has
two major components: structure learning and parameter learning, in which
structure learning is the basis of parameter learning and the premise of the
BN application. BN structure learning (BNSL) from data has great
significance and is also the main research direction of this paper. Due to
the search space growing super-exponentially with the increasing number of
nodes, BNSL has been proved to be an NPhard problem. At the same time,
evolutionary algorithms are a promising way to solve such problems. Genetic
algorithm (GA) has achieved many satisfying results these years but still
faces the problems of low search efficiency, low accuracy, and insufficient
integration with the problem. In this talk, the BNSL algorithm based on GA
is studied. First, the search behaviour of GA is improved by using BN
structural information. Besides, the superior information in the population
is mined by mutual information and population support. It is used to guide
GA to converge rapidly.
Keynote speakers in CSAI2022
.png)
Prof. Tao Xie
Peking University, China
Foreign Member of Academia Europaea
Fellow of ACM, Fellow of IEEE, Fellow of AAAS, Fellow of CCF
Peking University Chair Professor
Tao Xie is a Peking
University Chair Professor, a Deputy Director of the Key Lab of High
Confidence Software Technologies (PKU), Ministry of Education, and the
Deputy Secretary General of the Emerging Engineering Development
Committee of Peking University. He was a Full Professor at the
Department of Computer Science, the University of Illinois at
Urbana-Champaign (UIUC), USA. He is a Foreign Member of Academia
Europaea, a Fellow of ACM, IEEE, AAAS, and CCF. He won an Xplorer Prize,
NSFC Overseas Distinguished Young Scholar Award and its Extension
Category, NSF Faculty CAREER Award, ACM SIGSOFT Distinguished Service
Award, IEEE TCSE Distinguished Service Award, MSR Foundational
Contribution Award, TSE 2018 Best Paper Award, ASE 2021 Most Influential
Paper Award, etc. He serves as a Deputy Director of CCF TCSE, Chair of
CCF-IEEE CS Young Scientist Award Committee, Program Chair of China
National Computer Congress (CNCC 2020), Program Co-Chair of ICSE 2021,
Co-Editor-in-Chief of Wiley Journal of Software Testing, Verification
and Reliability (STVR), etc. His main research interests include
software engineering, system software, software security, trustworthy
AI.
Prof.Ninghui Li
Purdue University, USA
Fellow of ACM, Fellow of IEEE
Ninghui Li is a
Samuel D. Conte Professor of Computer Science at Purdue University. He
received a Bachelor's degree from the University of Science and
Technology of China (USTC) in 1993, and a Ph.D. in Computer Science from
New York University in 2000. His research interests are in security and
privacy, and he has published over 200 referred papers in these areas.
His 2007 paper ``t-Closeness: Privacy Beyond k-Anonymity and
l-Diversity'' received the ICDE 2017 Influential Paper award.
He is Editor-in-Chief for ACM Transactions On Privacy and Security since
October 2020, and has served as Program Chair for several leading
conferences in the field, including ACM CCS, ESORICS, ACM ASIACCS, ACM
SACMAT, and IFIP TM. He served as Chair of ACM Special Interest Group on
Security, Audit and Control (SIGSAC) from 2017 to 2021, and Vice Chair
from 2013 to 2017. He is ACM Fellow and IEEE Fellow.
Prof. Li's research has been supported by multiple NSF grants, including
an NSF CAREER award in 2005. His research has also been supported by Air
Force Office of Scientific Research (AFOSR), Army Research Office (ARO),
National Security Agency (NSA), IBM Research, Google, and Samsung. He
collaborated with Dr. Bertino on NSF and AFOSR funded projects.
Keynote speakers in CSAI2021
Prof. Benjamin W. Wah
The Chinese University of Hong Kong, Hong Kong
Fellow of the American
Association for the Advancement of Science
Fellow of IEEE; Fellow of the Association
for Computing Machinery
Wah was born in Hong Kong and graduated from Queen Elizabeth School, Hong Kong. He received his BS and MS in Electrical Engineering and Computer Science from Columbia University, USA, then furthered his studies at the University of California, Berkeley, obtaining an MS in Computer Science and a PhD in Databases.[1] Wah began his teaching career in Purdue University in 1979. He later joined the University of Illinois, Urbana-Champaign, in 1985, which he served until his retirement at the end of 2011.
In 1985-2011, he was the Franklin W. Woeltge Endowed Professor of Electrical and Computer Engineering at the University of Illinois, Urbana-Champaign, USA. In 2008-2009, he also served as Director of the Advanced Digital Sciences Center in Singapore, a US$50 million research center established by the University of Illinois in Singapore in collaboration with the Singapore government's Agency for Science, Technology and Research. In 1998–1999, Wah was Chair Professor of Computer Science and Engineering at The Chinese University of Hong Kong (CUHK), and in that year received an Exemplary Teaching Award. From 1999 to 2003, he served as Adjunct Professor in the Department of Computer Science and Engineering at CUHK. Between 2009-2019, he served as Provost of the Chinese University of Hong Kong.
Wah is an expert on non-linear programming, multimedia signal processing and artificial intelligence. He has published numerous research articles in top professional journals, such as Artificial Intelligence, IEEE Trans. in Computers, IEEE Trans. on Knowledge and Data Engineering, IEEE Trans. on Multimedia, IEEE Trans. on Parallel and Distributed Technology, IEEE Trans. on Software Engineering, Journal of Global Optimization, Journal of Artificial Intelligence Research. He is also the author of two books, and Editor-in-Chief of Wiley's Encyclopedia of Computer Science and Engineering (published in 2008), and has contributed to many edited books and book chapters. He has served on many journal editorial boards.
He also holds many Endowed Professorships and Honorary Professorships in leading universities in the United States of America and in Asia. Professor Wah was elected President of IEEE Computer Society in 2001. He was a member of the Research Grants Council of Hong Kong between 2005 and 2009 and Chairman of its Engineering Panel between 2006 and 2009. He has been a member of the HK Research Grants Council since 2011.
Professor Wah has received numerous honors and awards for his distinguished academic and professional achievements, including the Tsutomu Kanai Award, the W. Wallace McDowell Award, and the Richard E. Merwin Distinguished Service Award, all from the IEEE Computer Society, the Pan Wen Yuan Foundation Outstanding Research Award, and the IEEE Third Millennium Medal. In 2011, he received the Distinguished Alumni Award in computer science from the University of California, Berkeley. He has been elected: Fellow of the American Association for the Advancement of Science, Fellow of IEEE, Fellow of the Association for Computing Machinery.
Prof. Xiaodong LI, IEEE Fellow,
RMIT University, Melbourne, Australia
Xiaodong Li (M’03-SM’07-Fellow’20)
received his B.Sc. degree from Xidian University, Xi'an, China, and
Ph.D. degree in information science from University of Otago, Dunedin,
New Zealand, respectively. He is a Professor with the School of Science
(Computer Science and Software Engineering), RMIT University, Melbourne,
Australia. His research interests include machine learning, evolutionary
computation, neural networks, data analytics, multiobjective
optimization, multimodal optimization, and swarm intelligence. He serves
as an Associate Editor of the IEEE Transactions on Evolutionary
Computation, Swarm Intelligence (Springer), and International Journal of
Swarm Intelligence Research. He is a founding member of IEEE CIS Task
Force on Swarm Intelligence, a vice-chair of IEEE Task Force on
Multi-modal Optimization, and a former chair of IEEE CIS Task Force on
Large Scale Global Optimization. He is the recipient of 2013 ACM SIGEVO
Impact Award and 2017 IEEE CIS "IEEE Transactions on Evolutionary
Computation Outstanding Paper Award". He is an IEEE Fellow.