Speaker:

Prof. James CHENG
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Distributed data analytics frameworks lie at the heart of modern computing infrastructures in many organizations. In this talk, I’ll introduce my work on large-scale data analytics frameworks, including systems designed for specialized workloads (e.g. graph analytics, machine learning, high dimensional similarity search) and those for general workloads. I will also show some applications of these systems and their impact.

BIOGRAPHY:

James Cheng obtained his B.Eng. and Ph.D. degrees from the Hong Kong University of Science and Technology. His research focuses on distributed computing frameworks, large-scale graph analytics, and distributed machine learning.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Xin YANG
Associate Professor
School of Electronic Information and Communications
Huazhong University of Science and Technology

ABSTRACT:

Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection and diagnosis of PCa in mp-MRI images are highly desirable. In this talk I will introduce a series of our recent works on utilizing deep convolutional neural networks (CNN) for automated PCa detection and diagnosis. I will introduce our co-trained weakly-supervised CNNs which can concurrently identify the presence of PCa in an image and localize lesions. Our weakly-supervised CNNs are trained with entire prostate images with only image-level labels indicating the presence or absence of PCa, significantly alleviating the manual annotation efforts in clinical usage. I will also introduce our Tissue Deformation Network (TDN) for automated prostate detection and multimodal registration. The TDN can be directly integrated any PCa detection CNNs so that all parameters of the entire network can be jointly optimized in an end-to-end manner. In addition, I will describe our recent method for mp-MRI image synthesis based on generative adversarial learning.

BIOGRAPHY:

Xin Yang received her PhD degree in University of California, Santa Barbara in 2013. She worked as a Post-doc in Learning-based Multimedia Lab at UCSB (2013-2014). She joined Huazhong University of Science and Technology in August 2014 and is currently the Associate Professor of School of Electronic Information and Communications. Her research interests include medical image analysis, monocular simultaneous localization and mapping, and augmented reality. She has published over 40 technical papers, including TPAMI, TMI, MedIA, TMM, TVCG, ACM MM, MICCAI, ECCV, etc., co-authored two books and held 10+ U.S. and Chinese Patents and software copyrights.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Dr. Jingwei LU
Principal Software Engineer
Cadence Design Systems
Inc.

ABSTRACT:

ePlace is a flat and analytic VLSI placement algorithm using nonlinear optimization. We model every circuit component as a positive charge and approach the placement objective by simulating the respective electrostatic field. Placement density cost is defined as the total potential energy of the system. We proposed a modified Poisson’s equation and use spectral methods for numerical solution. We use Nesterov’s method instead of conjugate gradient method, where runtime bottleneck on line search is improved by our closed-form steplength predictor. Compared to prior placement research in literature, ePlace is theoretically sound and empirically promising. Experimental results show that ePlace outperforms all the published placers with better quality of results and shorter or comparable runtime. We have also extended our ePlace architecture to handle placement of mixed-size circuits and three-dimensional circuits and achieved consistently good performance.

BIOGRAPHY:

Jingwei Lu received his B.S. in information engineering from Zhejiang University, M.Phil. in computer engineering from The Hong Kong Polytechnic University, Ph.D. in computer science (computer engineering) from University of California, San Diego, respectively. He joined Cadence Design Systems, Inc. in 2014. His current research interests include analytic optimization of placement and other physical design automation problems.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

**** ALL ARE WELCOME ****

Speaker:

Prof. Nasir Rajpoot
Professor in Computational Pathology
Computer Science Department
Head of Tissue Image Analytics (TIA) Lab
University of Warwick

ABSTRACT:

The emerging discipline of Digital Pathology is poised to change the status quo in pathology practice for the better. The sheer size of multi-gigapixel images produced by digital slide scanners poses interesting technical challenges. On the other hand, the heap of image data linked with associated clinical and genomic data is a potential goldmine of invaluable information, as each image contains information about tens of thousands of cells and their spatial relationships with each other. There is now an appreciation that the practice of pathology can be significantly enhanced by direct involvement of image data scientists specialised in the analysis of information-rich, high-resolution whole-slide images which could be mined for the direct benefit of histological diagnosis and prognosis. I will present some of the recent developments in our group concerning digital pathology image analysis and tissue morphometrics from images of cancerous tissue slides. I will show that morphological motifs extracted from histology image data are likely to lead to novel prognostic data with relevance to personalised medicine. I will then discuss some of the main challenges in digital pathology and opportunities for exploring new unchartered territories.

BIOGRAPHY:

Nasir Rajpoot is Professor in Computational Pathology at the Computer Science department of the University of Warwick, where he started his academic career as a Lecturer (Assistant Professor) in 2001. He also holds an Honorary Scientist position at the Department of Pathology, University Hospitals Coventry & Warwickshire NHS Trust since 2016. Prof Rajpoot is the founding Head of Tissue Image Anayltics lab (formerly known as the BioImage Analysis or BIA lab) at Warwick since 2012. In Autumn 2017, he was awarded the Wolfson Fellowship by the UK Royal Society and the Turing Fellowship by the Alan Turing Institute, the UK’s national institute for data science and artificial intelligence.

Current focus of research in Prof Rajpoot’s lab is on developing algorithms for the analysis of large multi-gigapixel digital pathology images, with applications to computer-assisted grading of cancer and image-based markers for prediction of cancer progression and survival. Prof Rajpoot has been active in the digital pathology community for almost a decade now, having co-chaired several meetings in the histology image analysis (HIMA) series since 2008 and served as a founding PC member of the SPIE Digital Pathology meeting since 2012. He was the General Chair of the UK Medical Image Understanding and Analysis (MIUA) conference in 2010, and the Technical Chair of the British Machine Vision Conference (BMVC) in 2007. He is a Senior Member of IEEE and member of the ACM, the British Association of Cancer Research (BACR), the European Association of Cancer Research (EACR), and the American Society of Clinical Oncology (ASCO). Prof Rajpoot will be chairing the European Congress on Digital Pathology (ECDP) at Warwick in 2019.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Tsung-Yi HO
Professor
Department of Computer Science
National Tsing Hua University

ABSTRACT:

Continuous flow-based biochips are attracting more attention from biochemical and pharmaceutical laboratories due to the efficiency and low costs of these miniaturized chips. By processing fluid volumes of nanoliter size, such chips offer the advantages of fast reaction, high throughput, high precision and minimum reagent consumption. In addition, by avoiding human intervention in the whole experiment process with automated control, these chips provide the ability of reliable large-scale experiments and diagnoses to the biochemical and pharmaceutical industry. In this talk, the fundamentals of flow-based biochips will be introduced. Thereafter, the state-of-the-art of design automation for flow-based microfluidic biochips will be reviewed and specific features of these chips compared to integrated circuits will be presented. These features offer extensive chances to expand the design automation methods from the IC industry to develop customized design flows and architectures for flow-based microfluidic biochips.

BIOGRAPHY:

Tsung-Yi Ho received his Ph.D. in Electrical Engineering from National Taiwan University in 2005. He is a Professor with the Department of Computer Science of National Tsing Hua University, Hsinchu, Taiwan. His research interests include design automation and test for microfluidic biochips and neuromorphic computing systems. He has been the recipient of the Invitational Fellowship of the Japan Society for the Promotion of Science (JSPS), the Humboldt Research Fellowship by the Alexander von Humboldt Foundation, the Hans Fischer Fellowship by the Institute of Advanced Study of the Technische Universität München, and the International Visiting Research Scholarship by the Peter Wall Institute of Advanced Study of the University of British Columbia. He was a recipient of the Best Paper Awards at the VLSI Test Symposium (VTS) in 2013 and IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems in 2015. He served as a Distinguished Visitor of the IEEE Computer Society for 2013-2015, a Distinguished Lecturer of the IEEE Circuits and Systems Society for 2016-2017, the Chair of the IEEE Computer Society Tainan Chapter for 2013-2015, and the Chair of the ACM SIGDA Taiwan Chapter for 2014-2015. Currently, he serves as an ACM Distinguished Speaker and Associate Editor of the ACM Journal on Emerging Technologies in Computing Systems, ACM Transactions on Design Automation of Electronic Systems, ACM Transactions on Embedded Computing Systems, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, and IEEE Transactions on Very Large Scale Integration Systems, Guest Editor of IEEE Design & Test of Computers, and the Technical Program Committees of major conferences, including DAC, ICCAD, DATE, ASP-DAC, ISPD, ICCD, etc.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Weikang QIAN
Associate Professor
University of Michigan-Shanghai Jiao Tong
University Joint Institute at Shanghai Jiao Tong University

ABSTRACT:

As CMOS technology is scaled into the nanometer regime, power consumption has become one of the paramount concerns in designing VLSI circuits. At the same time, with the prevalence of mobile and embedded computing, there is an increasing demand for signal processing, multimedia, machine learning, and pattern recognition applications. One feature of these applications is that they can tolerate some error in the computation results. The relaxation of the accuracy requirement for these applications leads to a new design paradigm, known as approximate computing. It deliberately sacrifices a small amount of accuracy to achieve improvement in performance and power consumption. In this talk, I will first introduce the background on approximate computing. Then, I will present our research works in this area. The first topic is on design and analysis of approximate adder, which is a key building block in many error-tolerant applications, such as image processing and machine learning. The second topic is on logic synthesis algorithms for approximate computing, which explore the design space and return a good design that satisfies the error specification.

BIOGRAPHY:

Weikang Qian is an associate professor in the University of Michigan-Shanghai Jiao Tong University Joint Institute at Shanghai Jiao Tong University. He received his Ph.D. degree in Electrical Engineering at the University of Minnesota in 2011 and his B.Eng. degree in Automation at Tsinghua University in 2006. His main research interests include electronic design automation and digital design for emerging technologies. His research works were nominated for the Best Paper Awards at the 2009 International Conference on Computer-Aided Design (ICCAD) and the 2016 International Workshop on Logic and Synthesis (IWLS).

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Don Towsley
Distinguished University Professor
College of Information and Computer Science
University of Massachusetts – Amherst

ABSTRACT:

Quantum information processing is at the cusp of having significant impacts on technology and society in the form of providing unbreakable security, ultra-high-precision distributed sensing with applications to metrology and science discovery (e.g., LIGO), much higher-rate deep space optical communications than possible with conventional systems, and polynomial speeds up on graphical search with implications to big data. Most of these applications are enabled by high-rate distributed shared entanglement between pairs and groups of users. A critical missing component that prevents crossing this threshold is a distributed infrastructure in the form of a world-wide quantum network to enable this. This motivates our study of quantum networks, namely what the right architecture is and how to operate it, i.e., route multiple quantum information flows, and allocate resources fairly and dynamically.

In this talk we review a specific quantum network architecture and present opportunities and challenges related to resource sharing among multiple parties of users.  In particular, we focus on the determination of the capacity region associated with a particular network, i.e., characterize the vector of user entanglement rates that can be supported by the network.  Throughout the talk we will focus on issues related to resource allocation based on global/local state information and the benefits of path diversity.

BIOGRAPHY:

Don Towsley received a B.A. degree in physics and a Ph.D. degree in computer science, both from University of Texas University. He is currently a Distinguished University Professor in the College of Information and Computer Science at the University of Massachusetts – Amherst. Professor Towsley has been a Visiting Scientist at AT&T Labs – Research, IBM Research, INRIA, Microsoft Research Cambridge, and the University of Paris 6.

Professor Towsley’s research spans a wide range of activities from stochastic analyses of queueing models of computer and telecommunications to the design and conduct of measurement studies. He has performed some of the pioneering work on the exact and approximate analyses of parallel/distributed applications and architectures. More recently, he pioneered the area of network tomography and the use of fluid models for large networks.

Professor Towsley has been an editor of the IEEE Transactions on Communications, IEEE/ACM Transactions on Networking, and Journal of Dynamic Discrete Event Systems. He is currently on the Editorial boards of Networks and Performance Evaluation. He was a Program Co-chair of the joint ACM SIGMETRICS and PERFORMANCE ’92 conference. He is a two-time recipient of the Best Paper Award of the ACM Sigmetrics Conference.  He is a Fellow of the IEEE and of the ACM.  He is also a member of ORSA and is active in the IFIP Working Groups 6.3 on Performance Modeling of Networks and 7.3 on Performance Modeling. Towsley is the recipient of one of the IEEE’s most prestigious honors, the 2007 IEEE Koji Kobayashi Computers and Communications Award. He also received a UMass Amherst Distinguished Faculty Lecturer award in 2002 and a UMass Amherst College of Natural Sciences and Mathematics Faculty Research Award in 2003.  He also received the 2007 ACM SIGMETRICS Achievement Award, the 1999 IEEE Communications Society William Bennett Award, and several conference and workshop best paper awards. He is also the recipient of the University of Massachusetts Chancellor’s Medal and the Outstanding Research Award from the College of Natural Science and Mathematics at the University of Massachusetts.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Dr. Yanjing LI
Assistant Professor
Department of Computer Science (Systems Group)
University of Chicago

ABSTRACT:

Rapid advances in computing systems have transformed every aspect of life as we know it. However, we are now facing significant challenges in our quest for even more advanced computing systems. With significant vulnerability to failures and defects in CMOS and emerging technologies, hardware robustness is a key challenge for a large class of future computing systems — from edge devices all the way to cloud servers. Due to explosive growth in our dependency and demands on these systems, there is an urgent need to design robust systems that performs correctly despite underlying disturbances caused by hardware failures, design flaws, software bugs, environmental effects, and malicious attacks.

At the same time, exciting opportunities in robust system design also arise with innovations in new technologies and applications. In particular, machine learning has already achieved substantial breakthroughs in many computing domains and is expected to become even more prominent in the future. In this talk, we will explore the intersection of robust system design and machine learning from two different angels.

First, existing machine learning techniques may be effectively utilized to design efficient and low-cost robust systems. We will show an example where machine learning is used to guide dynamic soft error resilience tuning in microprocessors, leading to 2X improvement in overall energy efficiency compared to static hardening techniques, which up to now have been shown to be the one of the most efficient and effective soft error resilience approaches, without sacrificing reliability.

Second, robust systems optimized for efficient processing of machine learning applications are critical for pushing the frontiers of these applications. We will discuss our work on a direct-modulated optical interconnection network for large-scale interposer systems. Using multi-chip module GPUs as a case study, we find that our network design is capable of scaling up the number of streaming multiprocessors by up to 64X compared to the state-of-the-art today, while outperforming various competing designs in terms of energy efficiency, performance, and reliability. This will help satisfy the computing demands from future machine learning and other emerging applications.

BIOGRAPHY:

Dr. Yanjing Li is an Assistant Professor in the Department of Computer Science (Systems Group) at the University of Chicago. Prior to joining University of Chicago, she was a senior research scientist at Intel Labs. She received a Ph.D. in Electrical Engineering from Stanford University, and a M.S. in Mathematical Sciences (with honors) and a B.S. in Electrical and Computer Engineering (with a double major in Computer Science) both from Carnegie Mellon University. Her research interests lie broadly in computer architecture, emerging technologies, and VLSI design and validation. The focuses of her current research include interactions between computing systems and machine learning, photonic interconnects and processing, hardware security, and robust memory systems. She has won various awards including the NSF/SRC Energy-Efficient Computing: from Devices to Architectures (E2CDA) program, Intel Labs Gordy Academy Award (highest honor in Intel Labs), multiple Intel recognition awards, Outstanding Dissertation Award (European Design and Automation Association), Best Student Paper Award (IEEE International Test Conference), and the Best Paper Award (IEEE VLSI Test Symposium).

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Bin SHENG
Vice Director
Institute of Computer Application Department of Computer Science & Engineering Shanghai Jiao Tong University

ABSTRACT:

Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years. In this seminar, we focus on deep learning for medical big Data, especially on recent medical practice applications. In addition, we press on deep learning for medical 3D reconstruction and discuss the importance of 3D reconstruction in the field of medical analysis and modelling. At present, there have been deep learning methods for 3D reconstruction task, including reconstruction from single/multi-view images, learning spatial semantic context from volume data, and construction of new convolution methods to directly learn the topology distribution features on the raw mesh model, or use point cloud data for topology-free learning. We discuss some typical related work in deep learning methods on various 3D data structures, analyzing their affability to learning, flexibility, and geometrically manipulable for networks. At the end of the presentation, the design ideas, training results and applications of our DeepDR system for diabetic retinopathy are introduced.

BIOGRAPHY:

Bin Sheng received the Ph.D. degree in computer science from The Chinese University of Hong Kong, Hong Kong, in 2011. He is currently an Associate Professor with the Department of Computer Science and Engineering, and the vice director of the Institute of Computer Application, Shanghai Jiao Tong University. He is also an Adjunct Professor in Sungkyunkwan University, Korea. He serves as an Associate Editor of the IET Image Processing. His research interests include virtual reality, computer graphics, machine learning and medial image analysis. He was a visiting scholar in Utrecht University, Netherlands. He have published over on one hundred papers and applied over twenty patents. He was a recipient of the Best Paper Awards of CGI 2015, and has excellent research project reported worldwide by ACM TechNews.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Raymond NG
Professor
Department of Computer Science
University of British Columbia

ABSTRACT:

Personalized medicine has been hailed as one of the main frontiers for medical research in this century. In the first half of the talk, we will give an overview on our projects that use complex and big data sets for biomarker discovery. In the second half of the talk, we will describe some of the challenges involved in biomarker discovery. One of the challenges is the lack of quality assessment tools for data generated by ever-evolving genomics platforms. We will conclude the talk by giving an overview of some of the techniques we have developed on data cleansing and pre-processing.

BIOGRAPHY:

Raymond Ng is a Professor of Computer Science (Canada Research Chair in Data Science and Analytics Chief Informatics Officer, PROOF) and his main research area for the past two decades is on data mining, with a specific focus on health informatics and text mining. He has published over 200 peer-reviewed publications on data clustering, outlier detection, OLAP processing, health informatics and text mining. He is the recipient of two best paper awards – from the 2001 ACM SIGKDD conference, the premier data mining conference in the world, and the 2005 ACM SIGMOD conference, one of the top database conferences worldwide. For the past decade, he has co-led several large-scale genomic projects funded by Genome Canada, Genome BC and industrial collaborators. Since the inception of the PROOF Centre of Excellence, which focuses on biomarker development for end-stage organ failures, he has held the position of the Chief Informatics Officer of the Centre. From 2009 to 2014, Dr. Ng was the associate director of the NSERC-funded strategic network on business intelligence.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Yiyu Shi
Associate Professor
Department of Computer Science and Engineering
University of Notre Dame

ABSTRACT:

Biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. Since manual annotation suffers from limited reproducibility, arduous efforts, and excessive time, automatic segmentation is desired to process increasingly larger scale histopathological data. Towards this, deep neural networks (DNNs), particularly fully convolutional networks (FCNs), have been widely adopted. At the same time, quantization of DNNs has become an active research topic, which aims to represent weights with less memory (precision) to considerably reduce memory and computation requirements of DNNs with certain accuracy loss. In this talk, we will show that interestingly, quantization can be used as a method to reduce over-fitting in FCNs for better biomedical image segmentation accuracy. Extensive experiments on the MICCAI Gland dataset show that our method exceeds the current state-of-the-art performance by up to 1%.

BIOGRAPHY:

Dr. Yiyu Shi is currently an associate professor in the Department of Computer Science and Engineering at the University of Notre Dame, and the director of the Sustainable Computing Lab (SCL). He received his B.S. degree (with honor) in Electronic Engineering from Tsinghua University, Beijing, China in 2005, the M.S and Ph.D. degree in Electrical Engineering from the University of California, Los Angeles in 2007 and 2009 respectively. His current research interests include hardware intelligence and three-dimensional integration. In recognition of his research, many of his papers have been nominated for the Best Paper Awards in top conferences. He was also the recipient of IBM Invention Achievement Award, Japan Society for the Promotion of Science (JSPS) Faculty Invitation Fellowship, Humboldt Research Fellowship, IEEE St. Louis Section Outstanding Educator Award, Academy of Science (St. Louis) Innovation Award, Missouri S&T Faculty Excellence Award, NSF CAREER Award, IEEE Region 5 Outstanding Individual Achievement Award, and the Air Force Summer Faculty Fellowship. He has served on the technical program committee of many international conferences including DAC, ICCAD, DATE, ISPD, ASPDAC and ICCD. He is a member of IEEE CEDA Publicity Committee and IEEE Smart Grid R&D Committee, deputy editor-in-chief of IEEE VLSI CAS Newsletter, and an associate editor of IEEE TCAD, ACM JETC, VLSI Integration, IEEE TCCCPS Newsletter and ACM SIGDA Newsletter. He is also the chair of 2018 DAC System Design Contest on Machine Learning on Embedded Platforms.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:
Prof. James CHENG
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:
Distributed data analytics frameworks lie at the heart of modern computing infrastructures in many organizations. In this talk, I’ll introduce my work on large-scale data analytics frameworks, including systems designed for specialized workloads (e.g. graph analytics, machine learning, high dimensional similarity search) and those for general workloads. I will also show some applications of these systems and their impact.

BIOGRAPHY:
James Cheng obtained his B.Eng. and Ph.D. degrees from the Hong Kong University of Science and Technology. His research focuses on distributed computing frameworks, large-scale graph analytics, and distributed machine learning.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Kim-Fung Tsang
Associate Professor
Department of Electronic Engineering
City University of Hong Kong

ABSTRACT:

In Hong Kong, the Smart City Blueprint was announced in late 2017. Internet of Things (IoT) is one of the essential elements that thrives smart city projects. IoT will drive innovation and nurture collaboration across various disciplines and entities in the public, private and academic sectors. Nevertheless, there are still potential challenges to be resolved. This presentation discusses the important elements and building blocks that potentially lead to the success of smart city. Opportunities in applications such as smart metering, transportation, healthcare, communications etc. will be discussed.

BIOGRAPHY:

Ir Dr. Tsang Kim-Fung, PhD, CEng, FHKIE, SMIEEE, MIET

Ir Dr. KF Tsang is an Associate Professor in the Department of Electronic Engineering, City University of Hong Kong. He has published more than 200 technical papers and four books/book chapter. KF contributed to many Internet of Things (IoT) infra-structure designs. These include wireless home/office/building automation and energy management system, location tracking, healthcare, smart transportation,…. etc. KF is now devoting his effort to ZigBee and LPWAN development including LoRa, SigFox and NB IoT. As a result of his contribution, KF was award the IoT Heros Award in 2016 by GS1 IoT Council (nominated by Cisco).

To expedite IoT project development efficiency, KF has recently been approved by IEEE Standards Association to form a Working Group to develop the IEEE Standard P2668 for Maturity Index of Internet-of-things: Grading and ranking. The index will manifest guidance on blending of IoT solutions to evolve into better performance. The establishment of IoT Index shall proliferate a rapid, positive and mature progress of IoT industry.

Dr. Tsang is currently active in the following participation and capacities:

Internationally, the Chairman of IEEE Standard P2668 “IoT Index” Working Group; a member of the Working Group for “Wireless Best Practices on Factory Automation” for NIST, USA; a member of the Working Group for IEEE Standard “5G Interoperability”; Chairman of the Working Sub-Group on NB IoT for IEEE Standard “P1451 sensors”; Membership Champion of IEEE Industrial Electronics Society; Immediate Past Chairman of Technical Committee Cloud and Wireless Systems for Industrial Applications of the IEEE Industrial Electronics (IE) Society; Associate Editor of IEEE Transactions on Industrial informatics; Associate Editor of IEEE Industrial Electronics Magazine; Associate Editor of IEEE ITeN; Editor of TSII Transaction.

Locally, KF is the VP and Chairman of the IoT Committee, Smart City Consortium; Chairman of the “Internet of Things Special Users Group Hong Kong, Immediate Past Chairman of HKIE Electronics Division (2015-17).

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Dr. Tin Kam HO
Senior AI scientist and Development Manager
IBM Watson

ABSTRACT:

Data driven machine learning may interact with established domain knowledge in many ways. Learning algorithms can employ domain insight to obtain relevant feature designs and model structures. They can leverage unique data sources in training or apply contextual constraints to reduce errors. Domain experts can use predictions by the learned models to generate new hypotheses and make better decisions. Beyond these, a more ambitious pursuit is to ask: can task-oriented machine learning be used to build up domain knowledge continuously? What technologies may enable this and what are their limitations? We explore several research directions to address the challenges, highlighting the opportunities they offer in building towards evolving, accumulative artificial intelligence.

BIOGRAPHY:

Tin Kam Ho is a senior AI scientist and Development Manager at IBM Watson, working on cloud-hosted conversational systems and deep semantic analysis. Before, she led a department in statistics and machine learning research in Bell Labs. She pioneered research in multiple classifier systems, random decision forests, and data complexity analysis. Over her career she contributed to many pattern recognition applications such as multilingual reading machines, optical network design and monitoring, wireless geolocation, robotic radio survey, and smart grid demand forecasting. She served as Editor-In-Chief for Pattern Recognition Letters in 2004-2010, and as Editor or Associate Editor for several other journals including IEEE Transactions on Pattern Analysis and Machine Intelligence. Her work has been honored with the Pierre Devijver Award in statistical pattern recognition, in addition to several company and conference awards. She is an elected Fellow of the IAPR and the IEEE. She received a PhD in Computer Science from State University of New York at Buffalo in 1992, after graduating from CUHK in 1984.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Hanqiu Sun
VR
Visualization and Imaging Research Centre
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Stitching videos captured by mobile cameras that usually contain heavy shakiness and large parallax is practical but challenging. We propose the unified optimization of video stitching and stabilization that tackles the issues simultaneously. Since stitching relies on feature matches between input videos, and there inevitably exist false matches, we propose to encapsulate the false match elimination scheme and our optimization most optimally. The computed stabilization is the best for stitching, based on which we produce better stitching results compared to previous methods. We test the stitching and stability scores to evaluate the produced panoramic videos quantitatively. Wide-baseline street-view navigation is useful but challenging. We present a lightweight and efficient approach using homography computing and refining operators between input views. We combine homography fitting and propagation based on reliable/unreliable superpixels. We integrate the concepts of homography and mesh warping, and propose a novel homography constrained warping formulation that enforces smoothness between neighboring homographies. The proposed approach improves the state of the art, and shows that homography computation suffices for street-view navigation. Our experiments on city/rural datasets validate the efficiency and effectiveness of our approach.

BIOGRAPHY:

Prof. Sun received M.S. in electrical engineering from University of British Columbia, and Ph.D. in computer science from University of Alberta, Canada. Prof. Sun has published more than hundred technical papers refereed in VR/CG journals and international conferences, including MIT Journal of PRESENCE, Journal of Virtual Reality, IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Image Processing, IEEE Transactions on SMC, IEEE transactions on CSVT, ACM SIGGRAPH Asia, Computational Geometry, IEEE Transactions on Information Technology, Journal of Algorithms, Journal of Visual Languages and Computing, Journal of Applied Mathematics, IEEE journal of CGA, Computers & Graphics, Computer Graphics Forum, refereed book chapters and international conferences. She has served as guest editors of MIT PRESENCE, Journal of CAVW and IJIG, program co-chair of ACM VRST, organization co-chair of Pacific Graphics, CGI, CASA, director of advanced workshop on VR. Her current research interests include virtual reality, interactive modeling/rendering, image/video synopsis, computer-assisted surgery, fluids and Haptics simulations.

Tea, coffee and cookies will be provided after seminar.

Enquiries:  Ms. Crystal Tam at tel. 3943 8439

Speaker:

Dr. Jianli Chen
Center for Discrete Mathematics and Theoretical Computer Science
Fuzhou University

ABSTRACT:

The very large scale integration (VLSI) placement problem is NP-hard, and many placement constraints on a chip must be considered. It is a great challenge to design efficient and effective algorithms for the VLSI placement problem, especially for handling designs with millions of objects. In this talk, from the view of mathematical methods, I will try to discuss the characteristics of VLSI placement problem, and introduce some of our work on this problem.

BIOGRAPHY:

Dr. Jianli Chen is currently an Associate Professor at the Center for Discrete Mathematics and Theoretical Computer Science, Fuzhou University. He received the B.Sc. degree in information and computing sciences, the M.Sc. degree in computer application technology, and the Ph.D. degree in applied mathematics, all from Fuzhou University, in 2007, 2009, and 2012, respectively. His research interests include optimization theory and applications, and optimization methods for VLSI physical design automation. He has received three Best Paper Awards at the International Forum on Operations Research and Control Theory in 2011, the 13th FuJian Provincial Natural Science in 2014, and the 54th Design Automation Conference in 2017. He and his group was the recipient of the First Place Award at the CAD Contest at ICCAD in 2017. Dr. Chen has also received the Distinguished Young Scholars Foundation of FuJian Educational Committee in 2016, and the Outstanding Young Teacher Award of Fuzhou University (Top 1%) in 2017.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Tei-Wei Kuo
Computer Science & Information Engineering Department
National Taiwan University

ABSTRACT:

Software provides excellent and additional values to the designs of embedded systems, beside their hardware features. It closes the gap between user demands and hardware platforms. On the other hand, dilemma always exists on how to design software, such as modularity and optimization. In this talk, examples and solutions are presented for the designs of storage devices and embedded systems. The talk will be concluded with approaches in taking care of user perception in resource allocation for embedded systems.

BIOGRAPHY:

Tei-Wei Kuo received his B.S.E. and Ph.D. degrees in computer science from the National Taiwan University and the University of Texas at Austin in 1986 and 1994, respectively. He is a Distinguished Professor of the Department of Computer Science and Information Engineering and the Executive Vice President for Academics and Research, National Taiwan University, where he served as the Department Chairman from August 2005 to July 2008. Prof. Kuo served as a Distinguished Research Fellow and the Director of the Research Center for Information Technology Innovation, Academia Sinica, between January 20, 2015, and July 31, 2016. Prof. Kuo was the Program Director of the Computer Science Division of the Ministry of Science and Technology (2013-2015) and was an executive committee member of the IEEE Technical Committee on Real-Time Systems (2005-2017). He is an executive committee member of the IEEE Technical Committee on Cyber-Physical Systems and the Vice Chair of ACM SIGAPP. His expertise is embedded systems, non-volatile memory system and software, and real-time systems.

Prof. Kuo is an ACM Fellow and an IEEE Fellow. He is the Editor-in-Chief of the ACM Transactions on Cyber-Physical Systems and serves in the editorial board of the Journal of Real-Time Systems, IEEE Transactions on Industrial Informatics, and ACM Transactions on Transactions on Design Automation of Electronic Systems. He received the 2017 Outstanding Technical Achievement and Leadership Awards of the IEEE Technical Committee on Real-Time Systems, the 2017 Distinguished Leadership Award from the IEEE Technical Committee on Cyber-Physical Systems, the TECO Award in 2015, the ROC Ten Young Outstanding Persons Award in 2004, the Distinguished Research Award from the ROC National Science Council/Ministry of Science and Technology for three times, and the Young Scholar Research Award from Academia Sinica, Taiwan, ROC, in 2001.

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Professor Mahesan Niranjan
University of Southampton

ABSTRACT:

Classic machine learning is largely about classification and regression problems. However, many practical problems of interest in genomics, condition monitoring, medical diagnostics and security are better posed as problems of detecting novelty. In this talk, I will describe two applications of extracting useful information from novel data, in problems relating to modelling cellular protein concentrations and the solubility of synthetic chemical molecules. The algorithmic framework poses a robust support vector regression problem and the resulting non-convex optimisation problem is solved using a difference-of-convex formalism. (Part of this work is supported by grant EP/N014189/1, “Joining the Dots: From Data to Insight” from the EPSRC).

BIOGRAPHY:

Mahesan Niranjan is Professor of Electronics and Computer Science at the University of Southampton, UK. Prior to this appointment in 2008, he has held faculty positions at the Universities of Cambridge (1990-1998) and Sheffield (1999-2007). At the University of Sheffield, he has served as Head of Computer Science and as Dean of Engineering. His research interests are in the subject of Machine Learning, and he has worked on the algorithmic and applied aspects of the subject. Some of his work (e.g. the SARSA algorithm in Reinforcement Learning) have been fairly influential in the field. He has held several research grants from the Research Councils in the UK, and the European Union. Currently, his main focus is on architectures and algorithms for Deep Learning and inference problems that arise in computational biology. More information from:
https://www.ecs.soton.ac.uk/people/mn
https://scholar.google.co.uk/citations?user=3D3kuILUIAAAAJ

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Yufei Tao
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

The talk is about a popular form of density-based clustering that is known under the name “DBSCAN”. Progress has been made in recent years towards understanding its computational hardness. We will discuss the current lower and upper bounds, covering (i) both the static and dynamic (including “insertion-only”, and “insertions plus deletions”) settings, and (ii) both the exact and approximate versions.

BIOGRAPHY:

Yufei Tao is a Professor in the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He served as an associate editor of ACM Transactions on Database Systems (TODS) from 2008 to 2015, and of IEEE Transactions on Knowledge and Data Engineering (TKDE) from 2012 to 2014. He served as a PC co-chair of International Conference on Data Engineering (ICDE) 2014. He gave a keynote speech at International Conference on Database Theory (ICDT) 2016. He received two best-paper awards at SIGMOD (in 2013 and 2015, respectively), and a Google Faculty Research Award in 2017. He is an ACM distinguished scientist.

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Dr. Stevens Le Blond
Research Scientist
Éole polytechnique férale de Lausanne (EPFL)

ABSTRACT:

Humanitarian action, the process of aiding individuals in situations of crises, poses unique information-security challenges due to natural or manmade disasters, the adverse environments in which it takes place, and the scale and multi-disciplinary nature of the problems. Despite these challenges, humanitarian organizations are transitioning towards a strong reliance on digitalization of collected data and digital tools, which improves their effectiveness but also exposes them to computer
security threats. This talk presents the first academic effort seeking to understand and address the computer-security challenges associated with digitalizing humanitarian action.

First, I will describe a qualitative analysis of the computer-security challenges of the International Committee of the Red Cross (ICRC), a large humanitarian organization with over sixteen thousand employees, legal privileges and immunities, and over 150 years of experience with armed conflicts and other situations of violence worldwide. Second, I will present a research agenda to design and implement anonymity networks, block chains, and secure-processing systems addressing these challenges, and to deploy them in collaboration with the ICRC. I will close with a discussion on how to generalize our approach to provide digital immunity to humanitarian and other at-risk organizations.

BIOGRAPHY:

After having enjoyed sun bathing at INRIA Sophia-Antipolis, and actual bathing at the MPI-SWS, Stevens is now skiing in Switzerland where he’s a research scientist at EPFL. His Ph.D. thesis on the privacy analysis of the Skype protocol has led to privacy enhancements of the Skype architecture which is daily used by hundreds of millions of users. His post-graduate work on anonymity networks was qualified of the “[next generation] anonymity network closest to deployment” by ArsTechnica. He is one of the first academic researchers to have studied the computer security practices of politically-motivated attackers and their targets. His research has been published in leading conferences such as Oakland, Usenix Security, NDSS, SIGCOMM, and IMC.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Evangeline F.Y. Young
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

In this talk, I will briefly introduce the manufacturability issues in high performance microprocessors, followed by some discussions on related EDA (Electronic Design Automation) problems. Finally, we will focus on an interesting problem in this topic being solved by a fixed parametric tractable algorithm.

BIOGRAPHY:

Evangeline Young received her B.Sc. degree in Computer Science from The Chinese University of Hong Kong (CUHK). She received her Ph.D. degree from The University of Texas at Austin. She is currently a professor in the Department of Computer Science and Engineering in CUHK. Her research interests include algorithms and VLSI CAD. She is now working actively on floorplanning, placement, routing, DFM and EDA on Physical Design in general.

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Michael Rung-Tsong Lyu
Chairman and Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

In the next decade, Artificial Intelligent (AI) techniques can see wide adoption in our daily life to release human burden. In our recent Software Engineering research, we investigated on the design of novel AI methods to facilitate all three major phases in software engineering: development, operation, and analysis. In this talk, I will first introduce the AI techniques we employed, including machine learning framework, classification, clustering, matrix factorization, topic modeling, deep learning, and parallel computing platform. Then I will explain the challenges in each phase and describe our recently proposed methodologies. First in development phase, we suggested an automated code completion technique via deep learning. Our technique learns the code style from lots of existing code bases, and recommends the most suitable token based on the trained deep learning model and current coding context. Besides, to help developers in conducting effective logging, we designed a tool named LogAdvisor, which tells developers whether they should write a logging statement in the current code block or not. Secondly, in operation phase, we implemented a continuous and passive authentication method for mobile phones based on user touch biometrics. Different from the traditional password authentication scheme, our method can recognize malicious attackers based on abnormal user behaviors. Moreover, we developed PAID, which automatically prioritizes app issues by mining user reviews. Finally, in analysis phase, we designed systematic data analytics techniques for software reliability prediction. Besides, to make full use of the crucial runtime information, we proposed effective methods for every step in log analysis, including log parsing, feature extraction, and log mining. Furthermore, we developed a CNN-based defect prediction method to help developers find the buggy code. In the end, we expect to establish a comprehensive framework for systematic employment of AI techniques in the Software Engineering paradigm.

BIOGRAPHY:

Michael Rung-Tsong Lyu is a Professor and Chairman of Computer Science and Engineering Department at The Chinese University of Hong Kong. He worked at the Jet Propulsion Laboratory, the University of Iowa, Bellcore, and Bell Laboratories. His research interests include software reliability engineering, distributed systems, fault-tolerant computing, service computing, multimedia information retrieval, and machine learning. He has published 500 refereed journal and conference papers in these areas, which recorded 26,800 Google Scholar citations and h-index of 80. He served as an Associate Editor of IEEE Transactions on Reliability, IEEE Transactions on Knowledge and Data Engineering, and Journal of Information Science and Engineering. He is currently on the editorial boards of IEEE Transactions on Service Computing and Software Testing, Verification and Reliability Journal. He was elected to IEEE Fellow (2004), AAAS Fellow (2007), Croucher Senior Research Fellow (2008), IEEE Reliability Society Engineer of the Year (2010), and ACM Fellow (2015). Prof. Lyu received his B.Sc. from National Taiwan University, his M.Sc. from University of California, Santa Barbara, and his Ph.D. in Computer Science from University of California, Los Angeles.

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Ming-Ming Cheng
Professor
Nankai University

ABSTRACT:

Semantic segmentation of nature images is a fundamental problem in computer vision. While significant research progresses have been made in the last few years, the success of most existing method highly rely on large scale accurate pixel accurate annotations. However, humans effortlessly learn robust and accurate visual cognitive modes without the requirement of huge amount of pixel accurate semantic annotation. During childhood, we learn to robustly recognize and precisely locate the object regions with limited supervision from parents and other sources. Inspired by this process, our research focus on human cognitive inspired weakly supervised image understanding, by utilizing visual attention, category independent edge detection, region clustering etc., we observed consistent performance boost in weakly supervised image upstanding.

BIOGRAPHY:

Ming-Ming Cheng is a professor with CCCE, Nankai University. He received his PhD degree from Tsinghua University in 2012. Then he worked as a research fellow for 2 years, working with Prof. Philip Torr in Oxford. Dr. Cheng’s research primarily centers on algorithmic issues in image understanding and processing, including image segmentation, editing, retrieval, etc. He has published over 30 papers in leading journals and conferences, such as IEEE TPAMI, ACM TOG, ACM SIGGRAPH, IEEE CVPR, and IEEE ICCV. He has designed a series of popular methods and novel systems, indicated by 7000+ paper citations (2000+ citations to his first author paper on salient object detection). His work has been reported by several famous international media, such as BBC, UK telegraph, Der Spiegel, and Huffington Post.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Xiang Chen
Assistant Professor Volgenau School of Engineering George Mason University

ABSTRACT:

Mobile devices have become the horsepower of electronic industry in the past few years. During this burst period, more and more challenges have emerged regarding the usability, power consumption, security and computing efficiency of the mobile platforms. In the meantime, the presence of innovative devices and algorithms, such as the wearable devices and machine learning also provided extremely valuable research challenges and opportunities in the mobile system area.

In this talk, Dr. Xiang Chen will present his past research works mainly focusing on: (1) mobile computing acceleration for graphic and sensing system; (2) distributed mobile computing network design for machine learning based application; (3) and mobile security solution from interaction and machine learning perspectives. These works basically cover three design levels, from circuit to system and algorithms, giving a comprehensive overview of the challenges and opportunities of the mobile system development in the past few years.

BIOGRAPHY:

Xiang Chen received his Bachelor degree from the Northeastern University (China) in 2010, and his Ph.D. degree in ECE from the University of Pittsburgh in 2016. After the graduation, he joined the George Mason University as an Assistant Professor in the Department of Computer Engineering. His research interests include low power mobile computing, distributed mobile system and mobile security technology. He used to work in the Samsung and Microsoft Research Labs for mobile system research and network development. In the past years, he has published about 40 papers in the top international conferences and journals, and received several best paper awards and nominations form the Design Automation Conference (DAC), ICCAD, and ASPDAC.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Bingsheng He
Associate Professor
National University of Singapore

ABSTRACT:

Big data has become a buzz word. Among various big-data challenges, high performance is a must, not an option. We are facing the challenges (and also opportunities) at all levels ranging from sophisticated algorithms and procedures to mine the gold from massive data to high-performance computing (HPC) techniques and systems to get the useful data in time. How to leverage emerging hardware has become a hot research topic to tame the performance challenges of big data applications. Our research has been on the novel design and implementation of big data systems on emerging hardware (many-core CPUs, GPUs, and FPGAs etc). Interestingly, we have also observed the interplay between emerging hardware and big data systems. In this talk, I will present our research efforts in the past ten years and outline our research agenda on future hardware. More details about our research can be found at http://www.comp.nus.edu.sg/~hebs/.

BIOGRAPHY:

Dr. Bingsheng He is currently an Associate Professor at Department of Computer Science, National University of Singapore. Before that, he was a faculty member in Nanyang Technological University, Singapore (2010-2016), and held a research position in the System Research group of Microsoft Research Asia (2008-2010), where his major research was building high performance cloud computing systems for Microsoft. He got the Bachelor degree in Shanghai Jiao Tong University (1999-2003), and the Ph.D. degree in Hong Kong University of Science & Technology (2003-2008). His current research interests include cloud computing, database systems and high performance computing. His papers are published in prestigious international journals (such as ACM TODS and IEEE TKDE/TPDS/TC) and proceedings (such as ACM SIGMOD, VLDB/PVLDB, ACM/IEEE SuperComputing, ACM HPDC, and ACM SoCC). He has been awarded with the IBM Ph.D. fellowship (2007-2008) and with NVIDIA Academic Partnership (2010-2011). Since 2010, he has (co-)chaired a number of international conferences and workshops, including IEEE CloudCom 2014/2015 and HardBD2016. He has served in editor board of international journals, including IEEE Transactions on Cloud Computing (IEEE TCC) and IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS).

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Patrick Lee
Associate Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Data center storage systems increasingly adopt erasure coding to reduce the storage overhead of traditional 3-way replication. However, maintaining high performance in erasure-coded data center storage systems remains challenging. In this talk, I will present new results on how to seamlessly adapt erasure codes into data-center architectures. In particular, I will present repair pipelining, a general technique that speeds up the repair performance in erasure-coded storage, such that it can reduce the repair time to approximately the same as the normal read time by slicing the repair operation via a linear chain. This creates opportunities for applying erasure coding to frequently accessed data for high storage efficiency, while preserving read performance.

BIOGRAPHY:

Patrick Lee is now an Associate Professor of the Department of Computer Science and Engineering at the Chinese University of Hong Kong. He currently heads the Applied Distributed Systems Lab (http://adslab.cse.cuhk.edu.hk) and is working very closely with a group of graduate students on different projects in networks and systems. His research interests are in various applied/systems topics including storage systems, distributed systems and networks, operating systems, dependability, and security. Please refer to http://www.cse.cuhk.edu.hk/~pclee for Patrick’s papers and open-source software.

Tea, coffee and cookies will be provided after seminar.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Jin-Song Dong
Professor
National University of Singapore
Professor and Director
Institute for Integrated and Intelligent Systems
Griffith University

ABSTRACT:

The process analysis toolkit (PAT) integrates the expressiveness of state, event, time, and probability-based languages with the power of model checking. PAT currently supports various modeling languages with many application domains and has attracted thousands of registered users from hundreds of organizations. In this talk, we will present the PAT approach to “Event Analytics” (EA) which is beyond “Data Analytics”. The EA research is based on applying model checking to event planning, scheduling, prediction, strategy analysis and decision making. Various EA research directions will be discussed.

BIOGRAPHY:

Jin Song Dong completed his PhD from University of Queensland in 1995 and worked as research scientist at CSIRO from 1995-1998. Since 1998 Jin Song has been in the School of Computing at the National University of Singapore (NUS) where he received full professorship in 2016. His research is in the areas of formal methods, model checking, semantic technology, safety & security critical systems and probabilistic reasoning. He co-founded PAT reasoning system which has attracted 3000+ registered users from 900+ organizations in 72 countries. Currently, he is the lead Investigator for Singapore-UK joint project on smart grid security and privacy (with Andrew Martin at Oxford University). He is the co-investigator of “Securify: A Compositional Approach of Building Security Verified System”, “Trustworthy systems from untrusted Components”, and Singtel-NUS Cyber Security joint lab ($42M). Jin Song is on the editorial board of ACM Transaction on Software Engineering and Methodology and Formal Aspects of Computing. He has been a Visiting Fellow at Oxford University and a Visiting Professor at National Institute of Informatics, Japan. Recently he took a research director position at Institute for Integrated and Intelligent Systems at Griffith University. He has supervised 25 PhD students and many of them have become tenured faculty members in the leading universities around the world, including NTU, SUTD, HZUST, Monash U, Auckland U and Tianjin U.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Siu On Chan
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Approximating constraint satisfaction and related problems play a central role in the theory of approximation algorithms. These approximation algorithms, such as semidefinite programs and random walks, can be applied to a wide range of other problems, including scheduling and machine learning. In this talk, we mention recent results about the limitations of common approximation algorithms. This will reveal the complexity of many approximation problems and hopefully hint at better approximation algorithms for other problems.

BIOGRAPHY:

Prof. Siu On Chan got his BEng from The Chinese University of Hong Kong, MSc from University of Toronto, and PhD from UC Berkeley. He then worked as a postdoc researcher at Microsoft Research New England. He is an Assistant Professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He won Best Paper Award and Best Student Paper Award at STOC 2013.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Bei Yu
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Machine learning is a powerful technique that can derive knowledge from large data set, and provide prediction and modeling. Since VLSI chip designs have extremely high complexity and gigantic data, recently there has been a surge in applying and adapting machine learning to accelerate the design closure. In this talk, we focus on some key techniques and recent developments of machine learning on chips. Three design acceleration techniques and related applications will be covered: sparse representation, deep convolutional network; active learning based Pareto curve learning. We will also introduce our very recent work on accelerating convolution computation.

BIOGRAPHY:

Prof. Bei Yu received his Ph.D. degree from the Department of Electrical and Computer Engineering, University of Texas at Austin in 2014. He is currently an Assistant Professor in the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He has served in the editorial boards of Integration, the VLSI Journal and IET Cyber-Physical Systems: Theory & Applications. He has received four Best Paper Awards at ISPD 2017, SPIE Advanced Lithography Conference 2016, ICCAD 2013, and ASPDAC 2012, three other Best Paper Award Nominations at DAC 2014, ASPDAC 2013, ICCAD 2011, and four ICCAD/ISPD contest awards.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Chengmo Yang
Associate Professor
Department of Electrical and Computer Engineering
University of Delaware

ABSTRACT:

Non-volatile memory (NVM) technologies have been known for their advantages of large capacity, low energy consumption, high error-resistance, and near-zero power-on delay. It is expected that they will replace traditional SRAM as FPGA reconfigurable blocks. While NVMs promise FPGAs with more reconfigurable resources, lower power consumption, and higher resilience to power interruptions, they also impose two new design challenges: the slow write performance of NVMs may degrade FPGA reconfiguration speed, while their limited write endurance constrains FPGA programming cycles. None of these NVM features are taken into consideration in current FPGA synthesis tools, which have been optimized solely for SRAM-based FPGAs. To tackle this limitation, this talk presents a set approaches to tune the logic synthesis, placement and routing stages on FPGA synthesis flow to be NVM-friendly.

BIOGRAPHY:

CHENGMO YANG received the B.S. degree from Peking University, Beijing, China, and the M.S. and Ph.D. degrees from the University of California at San Diego, La Jolla, CA, USA. She is currently an Associate Professor with the Department of Electrical and Computer Engineering at the University of Delaware. Her research interests lie in the broad areas of computer architecture, embedded systems, and design automation, with a particular focus on improving reliability, security, non-volatility, and energy-efficiency of next generation computer systems. Dr. Yang received her NSF Career Award in 2013. She has published more than 50 technical papers at first-tier conferences and journals. She has 4 best paper awards and nominations. She serves/served as the program committee member of many conferences such as CODES-ISSS, DATE, HOST, ICCD, and LCTES.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Pan Hui
Nokia Chair University of Helsinki & HKUST

ABSTRACT:

Mobile Augmented Reality (MAR) is widely regarded as one of the most promising technologies in the next ten years. With MAR, we are able to blend information from our senses and mobile devices in myriad ways that were not possible before. The way to supplement the real world other than to replace real world with an artificial environment makes it especially preferable for applications such as tourism, navigation, entertainment, advertisement, and education. In this talk, I will first give an overview of the MAR research in our lab and then I will use two systems that we have developed as examples to illustrate the research challenges that we have to face for our research. These two MAR systems are Ubii – Ubiquitous Interface for Seamless Interaction between Digital and Physical Worlds, and Cardea – Context-aware Visual Privacy Protection from Pervasive Cameras. I will go through them in details.

BIOGRAPHY:

Professor Pan Hui received his PhD from the Computer Laboratory at University of Cambridge, and both his Bachelor and MPhil degrees from the University of Hong Kong. He is the Nokia Chair Professor in Data Science and Professor of Computer Science at the University of Helsinki. He is also the director of the HKUST-DT System and Media Lab at the Hong Kong University of Science and Technology and an adjunct Professor of social computing and networking at Aalto University. His research team is highly multicultural and international with researchers from over 12 countries. He believes diversity brews creativity and novelty. He was a senior research scientist and then a Distinguished Scientist for Telekom Innovation Laboratories (T-labs) Germany from 2008 to 2015. His industrial profile also includes his research at Intel Research Cambridge and Thomson Research Paris from 2004 to 2006. His research has been generously sponsored by Nokia, Deutsche Telekom, Microsoft Research, and China Mobile. He has published more than 200 research papers and with over 13,000 citations. He has 29 granted and filed European and US patents in the areas of augmented reality, mobile computing, and data science. He has founded and chaired several IEEE/ACM conferences/workshops, and has been serving on the organising and technical program committee of numerous top international conferences including ACM SIGCOMM, IEEE Infocom, ICNP, SECON, MASS, Globecom, WCNC, ITC, IJCAI, ICWSM and WWW. He is an associate editor for the leading journals IEEE Transactions on Mobile Computing and IEEE Transactions on Cloud Computing, and a guest editor for IEEE Communication Magazine and ACM Transactions on Multimedia Computing, Communications, and Applications. He is an ACM Distinguished Scientist and a newly elected IEEE Fellow.

Enquiries: Ms. Crystal Tam at tel. 3943 8439

Speaker:

Prof. Shengyu Zhang
Associate Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

In the last few years quantum computing has made significant progress in both theoretical development and physical implementation. In this talk, I’ll try to explain quantum mechanics from a mathematics perspective, and then briefly introduce quantum algorithms, quantum communication, physical implementation, and potential industry. The talk assumes no knowledge of quantum physics.

BIOGRAPHY:

Shengyu Zhang obtained his bachelor degree in mathematics, Fudan University in 1999, master in computer science, Tsinghua University in 2002, and Ph.D. in computer science, Princeton University in 2006. After working in NEC Laboratories America as a summer intern and in California Institute of Technology for a two-year postdoc, he joined The Chinese University of Hong Kong, where he is now an associate professor. His research interest lies in quantum computing, algorithm designing, and foundation of artificial intelligence. He is an editor of Theoretical Computer Science, and of International Journal of Quantum Information.

Enquiries: Mr. Calvin Tsang at tel. 3943 8440

Speaker:

Prof. Andrej Bogdanov
Associate Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

A secret sharing scheme is a mechanism for dividing up a secret among several parties so that unqualified subsets of the parties do not learn any information about the secret, while qualified subsets can recover the secret. Such schemes were introduced by Shamir and Blakley in 1979 and have become an indispensable component in the architecture of secure communication and computation protocols.

This talk will address the following foundational aspects of secret sharing and reconstruction:

1. Most secret sharing schemes are based on codes or polynomials. Is the use of linear algebra a necessity in this context or merely a convenience? What are “non-algebraic” schemes good for? What happens if they don’t exist?
2. In known secret sharing schemes, the shares are sometimes substantially larger than the secret. Is this loss in information efficiency a necessary price to pay for security?

Our methods (from joint works with Siyao Guo, Yuval Ishai, Ilan Komargodski, Emanuele Viola, and Christopher Williamson) highlight connections between secret sharing, approximation theory, and game theory.

BIOGRAPHY:

Andrej Bogdanov is associate professor of Computer Science and associate director of the Institute of Theoretical Computer Science and Communications at the Chinese University of Hong Kong. He obtained his B.Sc. and M.Eng. degrees from MIT and his Ph.D. from UC Berkeley. He has worked as a postdoctoral researcher at the Institute for Advanced Study in Princeton, at DIMACS (Rutgers University), and at ITCS (Tsinghua University), and as a visiting professor at the Tokyo Institute of Technology and at the Simons Institute for the Theory of Computing. His current research interests are in cryptography and the use of randomness in computation.

Enquiries: Mr. Calvin Tsang at tel. 3943 8440

Speaker:

Prof. Irwin Kuo-Chin KING
Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Online learning investigates sequential decisions with uncertainty, in which learning models generally are updated without reusing training samples. As data generated from sciences, business, governments, etc. are reaching petabyte or even Exabyte, and perform other characteristics (such as non-stationarity and imbalance), theories, models, and applications in online learning are becoming important in machine learning to process a large amount of streaming data effectively and efficiently. Recently, a number of online learning algorithms have been proposed to tackle sequential decisions with uncertainty, especially for cases of big data volume, non-stationary and/or highly imbalanced data. In this talk, we focus on some new developments of online learning technologies in both theory and applications. Relevant topics including Multi-Armed Bandits (MAB), online learning in stochastic settings, online learning with contextual information, and unsupervised online hashing, will be discussed. Moreover, some of our recent works such as combinatorial exploration of MAB, locality-sensitive linear bandits, online learning with imbalanced data, and faster online hashing, will also be presented to demonstrate how online learning approaches can be effectively applied to big data.

BIOGRAPHY:

Irwin King‘s research interests include machine learning, social computing, web intelligence, data mining, and multimedia information processing for Big Data. In these research areas, he has over 300 technical publications in journals and conferences. In addition, he has contributed over 30 book chapters and edited volumes. Prof. King is Associate Dean (Education), Faculty of Engineering and Professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He is also Director of the Shenzhen Key Laboratory of Rich Media and Big Data. He received his B.Sc. degree in Engineering and Applied Science from California Institute of Technology, Pasadena and his M.Sc. and Ph.D. degree in Computer Science from the University of Southern California, Los Angeles. Recently, Prof. King has been an evangelist in the use of education technologies in eLearning for the betterment of teaching and learning.

Enquiries: Mr. Calvin Tsang at tel. 3943 8440

Speaker:

Prof. Qiang XU
Associate Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

Conventional integrated circuit (IC) designs try all means to achieve error-free computation, even under worst-case combinations of process, voltage, and temperature (PVT) variations and wearout effects. As the above circuit non-idealities inevitably worsen with technology scaling, more design guardband has to be incorporated to ensure IC timing correctness. Consequently, such worst-case design methodology results in pessimistic designs with considerable power and performance overheads, lessening the benefits provided by technology scaling. On the other hand, emerging Recognition, Mining and Synthesis (RMS) applications demonstrate good intrinsic error-resilience property. They process noisy and redundant data sets obtained from non-traditional input sources such as various types of sensors (inexact inputs) and the associated algorithms are often stochastic in nature (e.g., iterative algorithms). Moreover, these applications usually do not require computing a unique or golden numerical result (“acceptable” instead of precise outputs). Consider two different classifiers that produce similar classification results on a set of example objects. It is very difficult, if not impossible, to tell which one is “better” for the classification of new objects.

With the above, in this talk, we present timing speculation techniques for better-than-worst-case (BTWC) design at circuit level and approximate computing techniques that relax the numerical equivalence between the specification and implementation of error-tolerant applications. By embracing errors in computing systems, we are able to achieve significant savings in energy and/or improvements in performance.

BIOGRAPHY:

Qiang Xu is an associate professor of Computer Science & Engineering at the Chinese University of Hong Kong. He leads the CUhk REliable laboratory (CURE Lab.), and his research interests include electronic design automation, fault-tolerant computing and trusted computing. Dr. Xu has published 150+ papers at referred journals and conference proceedings, and received two Best Paper Awards and five Best Paper Award Nominations. He is currently serving as an associate editor for IEEE Transaction on Computer-Aided Design of Integrated Circuits and Systems and Integration, the VLSI Journal.

Enquiries: Mr. Calvin Tsang at tel. 3943 8440

Speaker:

Prof. CAI Leizhen
Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

ABSTRACT:

An FPT (fixed-parameter tractable) algorithm confines the exponential running time of the algorithm by a parameter k, and therefore can solve NP-hard problems effectively when k is relatively small. The classical Vertex Cover problem requires us to determine whether a graph contains k vertices that cover all edges. In spite of its NP-hardness, the problem admits FPT algorithms, and the current fastest FPT algorithm solves the problem effectively for graphs with billions of vertices as far as k < 200. In comparison, an exhaustive search algorithm for the problem can hardly handle a graph with 100 vertices even for k = 10.

In this talk, we present three new and simple FPT algorithms for the Vertex Cover problem. For this purpose, we explore structural properties of vertex covers and use these properties to obtain FPT algorithms using colour coding, iterative compression, and indirect certificate methods. These new algorithms provide us with new insight into this classical problem.

BIOGRAPHY:

Prof. Cai received his PhD degree from the University of Toronto in 1992 and his main research interest resides in FPT algorithms for graph problems. He is particularly keen in designing simple and elegant algorithms, and is a co-inventor of an innovative random separation method for designing FPT algorithms. He has also initiated the study of structural parameters for FPT algorithms.

Enquiries: Ms Ricola Lo at tel 3943 8439

Speaker:

Mr. Jun-Yan ZHU
Ph.D. Candidate Berkeley AI Research (BAIR) Lab
Department of Electrical Engineering and Computer Sciences
University of California
Berkeley

ABSTRACT:

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image. In this talk, I will first investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. Using a training set of aligned image pairs, these networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.

Second, I will present an approach for learning to translate an image from a source domain to a target domain in the absence of paired examples. We exploit the property that translation should be “cycle consistent”, in the sense that if we translate, e.g., an sentence from English to French, and then translate it back from French to English, we should arrive back at the original sentence. Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

BIOGRAPHY:

Jun-Yan Zhu is a Ph.D. student at the Berkeley AI Research (BAIR) Lab, working on computer vision, graphics and machine learning with Professor Alexei A. Efros. He received his B.E. from Tsinghua University in 2012 and was a Ph.D. student at CMU from 2012-13. His research goal is to build machines capable of recreating the visual world. Jun-Yan is currently supported by the Facebook Graduate Fellowship.

Enquiries: Ms Ricola Lo at tel 3943 8439

Speaker:

Prof. Patrick C. K. Hung
Professor
Faculty of Business and Information Technology
University of Ontario Institute of Technology (UOIT)
Canada

ABSTRACT:

A toy is an item or product intended for learning or play, which can have various benefits to childhood development. Children’s toys have become increasingly sophisticated over the years, with a growing shift from simple physical products to toys that engage the digital world. Toy makers are seizing this opportunity to develop products that combine the characteristics of traditional toys such as dolls and stuffed toys with computing software and hardware. A smart anthropomorphism toy is defined as a device consisting of a physical toy component in the humanoid form that connects to a computing system through networking and sensory technologies to enhance the functionality of a traditional toy. Many studies found out that anthropomorphic designs resulted in greater user engagement. Children trusted such designs serve a good purpose and felt less anxious about privacy. While there have been many efforts by governments and international organizations such as UNICEF to encourage the protection of children’s data online, there is currently no standard privacy-preserving framework for mobile toy computing applications. Children’s privacy is becoming a major concern for parents who wish to protect their children from potential harms related to the collection or misuse of their private data, particularly their location. This talk presents the related research issues with a case study on Mattel’s Hello Barbie.

BIOGRAPHY:

Patrick C. K. Hung is a Professor at the Faculty of Business and Information Technology in University of Ontario Institute of Technology, Canada. Patrick has been working with Boeing Research and Technology at Seattle on aviation services-related research with two U.S. patents on mobile network dynamic workflow system. He currently works with the College of Technological Innovation at Zayed University on several smart city and cybersecurity research projects in the United Arab Emirates. He is also a Visiting Researcher at University of S瓊o Paulo, Brazil and National Technological University (UTN)-Santa Fe, Argentina. He is an Honorary International Chair Professor at National Taipei University of Technology in Taiwan and an Adjunct Professor at Nanjing University of Information Science & Technology in China. In addition, he was an Adjunct Professor at Wuhan University, a Visiting Researcher at the Shizuoka University and the University of Aizu in Japan, a Guest Professor in the University of Innsbruck in Austria, University of Trento and University of Milan in Italy. Before that, he was a Research Scientist with Commonwealth Scientific and Industrial Research Organization in Australia as well as he worked as a software engineer in the industry in North America. He is a founding member of the IEEE Technical Committee on Services Computing, the IEEE International Congress of Services and the IEEE Transactions on Services Computing. He is a Coordinating Editor of the Information Systems Frontiers. He has Ph.D. and Master in Computer Science from Hong Kong University of Science and Technology, Master of Applied Science in Management Sciences from the University of Waterloo, Canada and Bachelor in Computer Science from University of New South Wales, Australia.

Enquiries: Ms Ricola Lo at tel 3943 8439

Speaker:

Prof. Zhu Shanfeng
Associate Professor
Shanghai Key Lab of Intelligent Information Processing
School of Computer Science
Fudan University
Shanghai
China

ABSTRACT:

Multi-label learning deals with the classification problems where each instance can be assigned with multiple class labels simultaneously. There are thousands or even more labels in large-scale multi-label learning. Many important problems in bioinformatics can be modeled as a large scale multi-label learning problem. By utilizing learning to rank framework, we have developed MeSHLabeler and DeepMeSH to solve large-scale MeSH indexing problem, and DrugE-Rank to solve drug target interaction prediction problem. DeepMeSH achieved the first place in both BioASQ4 and BioASQ5 challenge, and MeSHLabeler achieved the first place in both BioASQ2 and BioASQ3 challenges. Specifically, DeepMeSH achieved a Micro F-measure of 0.6323, 2% higher than 0.6218 of MeSHLabeler and 12% higher than 0.5637 of MTI, for BioASQ3 challenge data with 6000 citations On the other hand, using benchmark data in DrugBank, experimental results show that DrugE-Rank outperforms competing methods significantly, especially achieving more than 30% improvement in Area under Prediction Recall curve for FDA approved new drugs and FDA experimental drugs.

BIOGRAPHY:

Shanfeng Zhu is an associate professor at School of Computer Science and Shanghai Key Lab of Intelligent Information Processing at Fudan University. He was awarded Ph.D. degree in Computer Science in 2003 at City University of Hong Kong. Before joining Fudan University in July 2008, he was a postdoctoral fellow at Bioinformatics Center, Kyoto University. He was a visiting Scholar in UIUC (March 2013-March 2014), and a visiting associate professor in Kyoto University (July 2016-Nov 2016). His research focuses on developing and applying machine learning and data mining methods for Bioinformatics, especially biomedical text mining, immunological informatics, drug discovery and protein function prediction.

Enquiries: Ms Ricola Lo at tel 3943 8439

Speaker:

Dr. Kim Batselier
Post-doctoral Research Fellow
Department of Electrical and Electronic Engineering
The University of Hong Kong

ABSTRACT:

Engineers nowadays are experiencing a tsunami of data. Social networks, DNA sequencing, smartphone apps and video games are generating an increasing amount of data. With these evergrowing amounts of information comes the need for new computational tools to analyze, model and infer patterns. Tensor methods are a viable solution to tackle these problems. This talk aims at giving a brief introduction to tensors and tensor methods. The goal is not to discuss too many topics but rather to teach the attendant the necessary “tensor tools” upon which the methods are based. The talk is at an introductory level and some basic prior knowledge of linear algebra is required.

BIOGRAPHY:

Kim Batselier graduated as an electrical engineer in 2005 from the University of Leuven, Belgium. He then started working at the private company BioRICS, where he developed algorithms for real-time modeling and monitoring of AC Milan football players during training at Milanello Sports Centre, Italy. In 2009, he went back to the electrical engineering department at the University of Leuven to pursue a PhD degree, which he obtained in 2013. During his PhD he developed a numerical linear algebra framework to solve problems on multivariate polynomials, with applications in bioinformatics, image processing and system identification. He has been a post-doctoral research fellow at The University of Hong Kong in the EEE department since 2013.

Enquiries:  Ms Ricola Lo at tel 3943 8439