Bio: Witold Pedrycz (IEEE Fellow, 1998) is Professor and Canada Research Chair (CRC) in Computational Intelligence in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. In 2009 Dr. Pedrycz was elected a foreign member of the Polish Academy of Sciences. In 2012 he was elected a Fellow of the Royal Society of Canada. Witold Pedrycz has been a member of numerous program committees of IEEE conferences in the area of fuzzy sets and neurocomputing. In 2007 he received a prestigious Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society. He is a recipient of the IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, and a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society.

His main research directions involve Computational Intelligence, fuzzy modeling and Granular Computing, knowledge discovery and data science, fuzzy control, pattern recognition, knowledge-based neural networks, relational computing, and Software Engineering. He has published numerous papers in this area. He is also an author of 16 research monographs and edited volumes covering various aspects of Computational Intelligence, data mining, and Software Engineering.

Dr. Pedrycz is vigorously involved in editorial activities. He is an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Int. J. of Granular Computing (Springer). He serves on an Advisory Board of IEEE Transactions on Fuzzy Systems and is a member of a number of editorial boards of international journals.

Topic: User-Centricity in Big Data Problems

Time: TBD.

Abstract: Big Data technology offers enormous potential and becomes a necessity in the era of omnipresent data. To unleash this potential, along with new paradigms, some existing principles need to be thoroughly revisited. As never seen so vividly before, the user assumes a central position in facilitating pursuits of big data by formulating some initial direction of the overall analysis and subsequently evaluating the value and actionability of the obtained findings. This entails that when considering the well-known list of Vs present in big data, the properties of value and veracity assume a pivotal role. The feature of user–centricity deserves a thorough discussion, especially in terms of defining the concept itself and identifying its multiway nature embracing transparency, interpretability, comprehension, and scalability.

The notions of abstraction and levels of abstraction, which are inherently involved in data analytics, can be conveniently realized in the form of information granules. The facet of abstraction (information granularity) makes the problems more manageable by positioning various constructs and processes at the level of a limited number of information granules. The abstraction mechanism is completed in the data space as well as feature (attribute) space resulting in granular data and granular features. Information granules can be sought as an outcome of realization of a generalized sampling mechanism.

In the talk, discussed are main ways of building information granules along with pertinent mechanisms of characterization of their quality and abilities to represent original data (reconstruction aspects). The tradeoffs present among the specificity of information granules, their abilities to describe the original data and related computing overhead are identified and quantified. Building a variety of models (predictors, classifiers, linkage analyzers, etc.) carried out in the presence of information granules (granular data) instead of original data comes with intriguing questions about the relevance of findings discovered at this particular level of abstraction, their comprehension and stability (robustness).

Bio: S.Y. Kung, Life Fellow of IEEE, is a Professor at Department of Electrical Engineering in Princeton University. His research areas include machine learning, data mining, systematic design of (deep-learning) neural networks, statistical estimation, VLSI array processors, signal and multimedia information processing, and most recently compressive privacy. He was a founding member of several Technical Committees (TC) of the IEEE Signal Processing Society. He was elected to Fellow in 1988 and served as a Member of the Board of Governors of the IEEE Signal Processing Society (1989-1991). He was a recipient of IEEE Signal Processing Society's Technical Achievement Award for the contributions on "parallel processing and neural network algorithms for signal processing" (1992); a Distinguished Lecturer of IEEE Signal Processing Society (1994); a recipient of IEEE Signal Processing Society's Best Paper Award for his publication on principal component neural networks (1996); and a recipient of the IEEE Third Millennium Medal (2000). Since 1990, he has been the Editor-In-Chief of the Journal of VLSI Signal Processing Systems. He served as the first Associate Editor in VLSI Area (1984) and the first Associate Editor in Neural Network (1991) for the IEEE Transactions on Signal Processing. He has authored and co-authored more than 500 technical publications and numerous textbooks including ``VLSI Array Processors'', Prentice-Hall (1988); ``Digital Neural Networks'', Prentice-Hall (1993) ; ``Principal Component Neural Networks'', John-Wiley (1996); ``Biometric Authentication: A Machine Learning Approach'', Prentice-Hall (2004); and ``Kernel Methods and Machine Learning”, Cambridge University Press (2014).

Topic: MINDnet: a methodical  and cost-effective learning paradigm for training deep neural networks

Time: TBD.

Abstract: We shall first introduce two basic machine learning subsystems: (1) Feature Engineering (FE), e.g. CNN for image/speech feature extraction and (2) Label Engineering (LE), e.g. Multi-layer Perceptron (MLP). It is also important that we stress both the strength of weakness of deep learning. For the former, the success of deep neural networks (DNN) hinges upon the rich nonlinear space embedded in their nonlinear hidden neuron layers. As to the weakness, the prevalent concerns over deep learning include two major fronts: one analytical and one structural.

From the analytical perspective, the ad hoc nature of deep learning renders its success at the mercy of trial-and-errors. To rectify this problem, we advocate a methodic learning paradigm, MINDnet, which is computationally efficient in training the networks and yet mathematically feasible to analyze. MINDnet hinges upon the use of an effective optimization metric, called Discriminant Information (DI). It will be used as a surrogate of the popular metrics such as 0-1 loss or prediction accuracy. Mathematically , DI is equivalent or closely related to Gauss’ LSE, Fisher’s FDR, and Shannon’s Mutual Information. We shall explain why is that higher DI means higher linear separability, i.e. higher DI means that the data are more discriminable. In fact, it can be shown that, both theoretically and empirically, a high DI score usually implies a high prediction accuracy.

In the structural front, the curse of depth it is widely recognized as a cause of serious concern. Fortunately, many solutions have been proposed to effectively combat or alleviate such a curse. Likewise, in our case, MINDnet offers yet another cost-effective solution by circumventing the depth problem altogether via a new notion (or trick) of omni-present supervision, i.e. teachers hidden a “Trojan-horse” being transported (along with the training data) from the input to each of the hidden layers. Opening up the Trojan-horse at any hidden-layer, we can have direct access to the teacher’s information for free, in the sense that no BP is incurred. In short, it amount to learning with no-propagation (NP). By harnessing the teacher information, we will be able to construct a new and slender “inheritance layer” to summarize all the discriminant information amassed by the previous layer. Moreover, by horizontally augmenting the inheritance layer with additional randomized nodes and applying back-propagation (BP) learning, the discriminant power of to the newly augmented network will be further enhanced.

In our experiments, the MINDnet was applied to several real-world datasets, including CIFAR-10 dataset reported below. As the baseline of comparison, the highest prediction accuracies published in recent years are: 93.57% (ResNet, 2015) < 96.01% (DenseNet, 2016) < 97.35% (NAS-Net, 2018) For fairness, we applied both MINDnet and MLP(with ReLU/dropout) to the same 64-dimensional feature vectors extracted by ResNET. Our results shows that MINDnet can deliver a substantial margin of improvement - up by nearly 5% over the original baseline of 93.57%. In short, MINDnet has the highest performance so far: 98.26% (MINDnet, 2018).

In summary, MINDnet advocates a new learning paradigm to Monotonically INcrease the Discriminative power (quantified by DI) of the classifying networks. It offers a new LE learning model to efficiently tackle both the afore-mentioned analytical and structural concerns over deep learning networks.

Bio: Dr. Bhavani Thuraisingham is the Louis A. Beecherl, Jr. Distinguished Professor of Computer Science and the Executive Director of the Cyber Security Research and Education Institute (CSI) at The University of Texas at Dallas. She is an elected Fellow of IEEE, the AAAS, the British Computer Society, and the SPDS (Society for Design and Process Science). She received several prestigious award including IEEE Computer Society's 1997 Technical Achievement Award for “outstanding and innovative contributions to secure data management”, the 2010 ACM SIGSAC (Association for Computing Machinery, Special Interest Group on Security, Audit and Control) Outstanding Contributions Award for “seminal research contributions and leadership in data and applications security for over 25 years” and the SDPS Transformative Achievement Gold Medal for her contributions to interdisciplinary research. She has unique experience working in the commercial industry (Honeywell), federal research laboratory (MITRE), US government (NSF) and academia and her 35 year career includes research and development, technology transfer, product development, program management, and consulting for the federal government. Her work has resulted in 100+ journal articles, 200+ conference papers, 100+ keynote and featured addresses, eight US patents (three pending) and fifteen books (two pending). She received the prestigious earned higher doctorate degree (DEng) from the University of Bristol England in 2011 for her published work in secure data management since her PhD. She has been a strong advocate for women in computing and has delivered featured addresses at events organized by the CRA-W (Computing Research Association) and SWE (Society for Women Engineers).

Topic: TBD

Time: TBD.

Abstract: TBD

Bio: Jie Wu is a Chinese computer scientist. He is the Associate Vice Provost for International Affairs and Director for Center for Networked Computing at Temple University. He also serves as the Laura H. Carnell professor in the Department of Computer and Information Sciences. He served as Program Director of Networking Technology and Systems (NeTS) at the National Science Foundation from 2006 to 2008. Jie Wu is noted for his research in routing for wired and wireless networks. His main technical contributions include fault-tolerant routing in hypercube-based multiprocessors, local construction of connected dominating set and its applications in mobile ad hoc networks, and efficient routing in delay tolerant networks, including social contact networks.

He served as the General Chair of IEEE ICDCS 2013, IEEE IPDPS 2008, and IEEE MASS 2006 and the Program Chair of CCF CNCC 2013, IEEE INFOCOM 2011, and IEEE MASS 2004. He is a Fellow of IEEE and serves on the editorial board for a number of journals, including IEEE Transactions on Computers (TC), IEEE Transactions on Services Computing (TSC), and Journal of Parallel and Distributed Computing (JPDC). He received 2011 China Computer Federation (CCF) Overseas Outstanding Achievements Award. He was a Fulbright Senior Specialist. He was also an IEEE Distinguished Visitor and an ACM Distinguished Speaker and is currently a CCF Distinguished Speaker.

Topic: TBD

Time: TBD.

Abstract: TBD

Bio: Professor Xiaodong Wang was an assistant professor from July 1998 to December 2001 at the Department of Electrical Engineering at Texas A&M University. In January 2002, he joined the Department of Electrical Engineering at Columbia University as an assistant professor. Dr. Wang's research interests fall in the general areas of computing, signal processing, and communications. He has worked and published extensively in the areas of wireless communications, statistical signal processing, parallel and distributed computing, nanoelectronics, and quantum computing. Dr. Wang has received the 1999 NSF CAREER Award. He has also received the 2001 IEEE Communications Society and Information Theory Society Joint Paper Award.

Topic: TBD

Time: TBD.

Abstract: TBD

Bio: Ruqian Lu is a professor of computer science of the Institute of Mathematics, Academy of Mathematics and Systems Science, at the same time an adjunct professor of Institute of Computing Technology, Chinese Academy of Sciences and Peking University. He is also a fellow of Chinese Academy of Sciences. His research interests include artificial intelligence, knowledge engineering, knowledge based software engineering, formal semantics of programming languages and quantum information processing. He has published more than 180 papers and 10 books. He has won two first class awards from the Chinese Academy of Sciences and a National second class prize from the Ministry of Science and Technology. He has also won the 2003 Hua Loo-keng Mathematics Prize from the Chinese Mathematics Society and the 2014 lifetime achievements award from the China’s Computer Federation.

Topic: Next to Big Data is Big Knowledge

Time: TBD.

Abstract: Recently, the topic of mining big data to obtain knowledge (called big data knowledge engineering) has become hot interest of researchers. Also the concept of big knowledge was coined in this process. The new challenge was to mine big knowledge (not just knowledge) from big data. While researchers used to explore the basic characteristics of big data in the past, it seems that very few or even no researcher has tried to approach the problem of defining or summarizing the basic characteristics of big knowledge. This talk will first provide a retrospective view on the research of big data knowledge engineering and then introduce formally the big knowledge concept with five major characteristics, both qualitatively and quantitatively. Using these characteristics we investigate six large scaled knowledge engineering projects: the Shanghai project of fifth comprehensive investigation on city’s traffic, the Xia-Shang-Zhou chronology project, the Troy city and Trojan War excavation, the international human genome project, the Wiki-world project and the currently very hot research on knowledge graphs. We show that some of them are big-knowledge projects but some aren’t. Based on these discussions, the concept of big-knowledge system will be introduced with additional five characteristics. Also big-knowledge engineering concepts and their lifecycle models are introduced and discussed. At last, a group of future research problems on big knowledge is proposed.