Title
Duality of Mining Problems

Abstract
Frequent-itemset mining and erasable-itemset mining are two commonly seen and practical techniques for finding different useful itemsets in data mining. Frequent-itemset mining is a significant pre-processing step in the search for association rules and is mainly conducted based on the frequencies of the itemsets in a transaction database. On the other hand, erasable-itemset mining is often applied to product production planning and identifies the itemsets that would not significantly impact production profits if removed. Although the two mining techniques seem to be different and independent, we have derived they are actually equivalent to each other. We formally prove that these two mining techniques possess the property of duality. We design methods to transform one of the two mining problems into the other and then solve it, and vice versa. The mining results with and without the transformation will be identical. We then extend the duality property of the two mining problems to multiple-threshold and weighted-item situations. With the duality property, we can easily design an algorithm from its corresponding one in the dual mining problem.

Biodata
Tzung-Pei Hong received his Ph.D. degree in computer science and information engineering from National Chiao-Tung University in 1992. He served as the first director of the library and computer center, the Dean of Academic Affairs, and the Vice President in the National University of Kaohsiung, Taiwan. He is currently a chair and distinguished professor at the Department of Computer Science and Information Engineering in NUK, and a joint professor at the Department of Computer Science and Engineering, National Sun Yat-sen University, Taiwan.
He has published more than 600 research papers in international/national journals and conferences and has planned more than fifty information systems. He is also the board member of more than forty journals and the program committee member of more than one thousand conferences. His current research interests include knowledge engineering, data mining, soft computing, management information systems, and www applications.

Title
Neverending Machine Learning

Abstract
Lifelong Machine Learning (LLML) can overcome the limitations of statistical learning algorithms that need many training examples and are suitable for isolated single-task learning. Key features that need to be developed within such systems to benefit from prior learned knowledge include feature modeling, knowledge retaining from past learning tasks, knowledge transfer to future learning tasks, previous knowledge updates, and user feedback.
Also, the concept of task that appears in many formal definitions of lifelong ML models seems hard to define in many real-life setups because it is often difficult to distinguish when a particular task finishes and subsequent starts.
One of the main challenges is the stability and plasticity dilemma, where the learning systems have to trade-off between learning new information without forgetting the old one. It is visible in the catastrophic forgetting phenomenon, which is defined as a complete forgetting of previously learned information by a neural network exposed to the new information.
The talk will focus on the main approaches related to Lifelong Machine Learning and the open challenges in this domain.

Biodata
Michał Woźniak is a professor of computer science at the Department of Systems and Computer Networks, Wroclaw University of Science and Technology, Poland. His research focuses on machine learning, compound classification methods, classifier ensembles, data stream mining, and imbalanced data processing. Prof. Wozniak has been involved in research projects related to the topics mentioned above and has been a consultant for several commercial projects for well-known Polish companies and public administration. He has published over 300 papers and three books. Prof. Wozniak was awarded numerous prestigious awards for his scientific achievements as IBM Smarter Planet Faculty Innovation Award (twice) or IEEE Outstanding Leadership Award, and several best paper awards from the prestigious conferences.

Title
Flexible Retrieval System for Visual Lifelog Exploration

Abstract
People create a huge collection of photos and videos to capture daily activities as well as special moments in their lives. Such visual and related metadata are valuable sources for lifelog retrieval, not only to revive memories or to verify events but also to analyze for a better understanding of our behaviors and habits. This can help re-design business processes, create better personalized intelligent services, improve personal lifestyle and health, etc.
In this presentation, we will discuss different solutions for flexible interactive retrieval systems to explore visual lifelog with multiple modalities for interaction and query processing, including visual query by meta-data, text query and visual information matching based on a joint embedding model, scene clustering based on visual and location information, flexible temporal event navigation, and query expansion with visual examples.

Biodata
MINH-TRIET TRAN (Member, IEEE) received the B.Sc., M.Sc., and Ph.D. degrees in computer science from University of Science, VNU-HCM, in 2001, 2005, and 2009. In 2001, he joined University of Science. He was a Visiting Scholar with the National Institutes of Informatics (NII), Japan, from 2008 to 2010, and the University of Illinois at Urbana–Champaign (UIUC), from 2015 to 2016. His research interests include cryptography, security, computer vision, and human–computer interaction.
He is currently the Vice President of University of Science, VNU-HCM, and Director of John von Neumann Institute, VNU-HCM. He is also Membership Development, Student Activities Coordinator of IEEE Vietnam. He is also a member of the Advisory Council for Artificial Intelligence development of Ho Chi Minh City, and Vice President of Vietnam Information Security Association (VNISA, South Branch)

Title
Natural Language Processing for Legal Engineering and its Application

Abstract
Our society is regulated by a lot of laws that are related mutually. When a society is viewed as a system, laws can be viewed as the specifications for society. In the upcoming e-Society, laws have more important roles in achieving a trustworthy society and we expect a methodology that treats a system-oriented aspect of laws. Legal Engineering is the field that studies the methodology and applies information science, software engineering, and artificial intelligence to laws for supporting legislation and implementing laws using computers. As laws are written in natural language, natural language processing is essential for Legal Engineering. In this talk, we present our works on natural language processing for Legal Engineering. We also highlight our current deep learning-based techniques for analyzing legal documents and our system participating in the Competition on Legal Information Extraction/Entailment competitions in which we won an outstanding result.

Biodata
Minh Le Nguyen received the B.Sc. degree in computer science from Hanoi National University, Hanoi, Vietnam, in 1998, the master’s degree from the College of Technology, Vietnam National University, Hanoi, in 2001, and the Ph.D. degree in information science from the Graduate School of Information Science, JAIST, Ishikawa, Japan, in 2004. He is currently working as a Professor with the Graduate School of Information Science, JAIST. He is also a director of the Interpretable AI center at JAIST. His research interests include machine learning, text summarization, machine translation, natural language understanding, artificial intelligence, legal engineering, and grammatical analysis of music.