Seminar of Technologies Supporting AI Applications
- Online presentation via Zoom
- Singapore Time/ UTC+8
Artificial intelligence (AI) enables a wide range of computing and networking applications and services in the next generation of edge networks, for example, smart cities, autonomous driving systems, cognitive computing, speech recognition, and Metaverse. This series of research seminars involves research talks from well-known professors who are working on the area of AI and applications and technologies in AI. In addition, the professors will present their current research works and introduce the cutting-edge research works in various aspects of AI.
For the first speaker, Zehui Xiong is an assistant professor in the Pillar of Information Systems Technology and Design, Singapore University of Technology and Design (SUTD), Singapore. In his talk, Professor Zehui Xiong will introduce concepts of Blockchain and Federated Learning. He will discuss a case study on incomplete information of incentive mechanism design for Federated Learning based on Blockchain and Bayesian game theory. For the second speaker, AhHwee Tan is Professor of Computer Science and Associate Dean (Research) at the School of Computing and Information Systems (SCIS), Singapore Management University (SMU). In his talk, Professor Ah-Hwee Tan will introduce a selforganizing neural network approach and present the case studies that can be solved by the approach. For the third speaker, Dusit Niyato is a professor in the School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU), Singapore. In his talk, Professor Dusit Niyato will introduce concepts of Metaverse and virtual service management. He will introduce game theoretic approaches for Metaverse virtual service management. For the fourth speaker, Chng Eng Siong is an associate professor in the School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU), Singapore. In his talk, Professor Chng Eng Siong will share his research work about developing codes-switching English/Mandarin speech recognition.
Program and time table:
|Speaker||Topics||Date||Time (Singapore)||Time (Thailand)|
|Prof. Xiong Zehui, Singapore University of Technology and Design||Blockchain-empowered Federated Learning||2 August 2022, Tuesday||10.00 a.m. – 11.00 a.m.||9.00 a.m. – 10.00 a.m.|
|Prof. Tan Ah Hwee, Singapore Management University||AI and Cognitive Computing: A Self-Organizing Neural Network Approach||2 August 2022, Tuesday||2.00 p.m. – 3.00 p.m.||1.00 p.m. – 2.00 p.m.|
|Prof. Dusit Niyato, Nanyang Technological University||Metaverse Virtual Service Management: Game Theoretic Approaches||4 August 2022, Thursday||2.00 p.m. – 3.00 p.m.||1.00 p.m. – 2.00 p.m.|
|Prof.Chng Eng Siong, Nanyang Technological University||Recent Progress in Large Vocabulary Continuous Speech Recognition||4 August 2022, Thursday||4.00 p.m. – 5.00 p.m.||3.00 p.m. – 4.00 p.m.|
Blockchain-empowered Federated Learning
2 August 2022 | 10.00 a.m. – 11.00 a.m. (Singapore Time/ UTC+8)
Prof. Zehui Xiong
Singapore University of Technology and Design
Abstract: Blockchain is truly the foundation for web 3.0, especially as a trust machine of decentralized organization. Federated learning is a distributed machine learning framework, which can effectively protect the privacy of data owners, but it still faces challenges such as free-riding, unfairness, and unreliability. In this presentation, we first briefly introduce major concepts of two technologies including Blockchain and Federated Learning (FL). Then, we discuss a case study on incomplete information of incentive mechanism design for FL based on blockchain and Bayesian game theory. Therein, the data transaction process is modeled by quantifying the cost-utility of the data owners and the payment reward of the data requesters, in which Shapley value is used to realize the fairness of reward distribution of data owners. Then, the resource allocation strategies of the data owners are constructed as a Bayesian game, which realizes several promising incentive properties by optimizing the local training strategy. Furthermore, a privacy-preserving Bayesian game action strategy consensus algorithm is proposed to enable the data owners to realize the Bayesian Nash equilibrium for data trading based on blockchain. We also show that the proposed mechanism ensures the fairness of reward distribution and the credibility of resource allocation. Simulation experiments and performance evaluations based on real datasets demonstrate the effectiveness of the proposed design. Lastly, some possible future research directions will be discussed.
Bio: Zehui Xiong is currently an Assistant Professor in the Pillar of Information Systems Technology and Design, Singapore University of Technology and Design. Prior to that, he was a researcher with Alibaba-NTU Joint Research Institute, Singapore. He received the PhD degree in Nanyang Technological University, Singapore. He was the visiting scholar at Princeton University and University of Waterloo. His research interests include wireless communications, network games and economics, blockchain, and edge intelligence. He has published more than 150 research papers in leading journals and flagship conferences and many of them are ESI Highly Cited Papers. He has won over 10 Best Paper Awards in international conferences and is listed in the World’s Top 2% Scientists identified by Stanford University. He is now serving as the editor or guest editor for many leading journals including IEEE JSAC, TVT, IoTJ, TCCN, TNSE, ISJ, JAS. He is the recipient of IEEE TCSC Early Career Researcher Award for Excellence in Scalable Computing, IEEE TEMS Technical Committee on Blockchain and Distributed Ledger Technologies Early Career Award, IEEE CSIM Technical Committee Best Journal Paper Award, IEEE SPCC Technical Committee Best Paper Award, IEEE VTS Singapore Best Paper Award, Chinese Government Award for Outstanding Students Abroad, and NTU SCSE Best PhD Thesis Runner-Up Award. He is the Founding Vice Chair of Special Interest Group on Wireless Blockchain Networks in IEEE Cognitive Networks Technical Committee.
AI and Cognitive Computing: A Self-Organizing Neural Network Approach
2 August 2022 | 2.00 p.m. – 3.00 p.m. (Singapore Time/ UTC+8)
Prof. Tan Ah Hwee
Professor of Computer Science, Associate Dean (Research), Jubilee Technology Fellow
Singapore Management University
Abstract: Although recent development in machine learning, in particular deep learning, has significantly advanced the field of Artificial Intelligence (AI), data-driven learning-based AI systems are typically designed to solve specific problems by learning from a vast amount of training data. Human cognition, on the other hand, involves a complex interplay of multiple high-level functions, notably self-awareness, memory, reasoning, learning, and problem solving. In this talk, we shall introduce a new computing paradigm known as Cognitive Computing, which is inspired by human cognitive functions and processes. Specifically, we discuss how a family of self-organizing neural network models, collectively known as fusion Adaptive Resonance Theory (fusion ART), may be used to simulate cognitive computation. By extending the Adaptive Resonance Theory (ART) into a multi-channel network architecture, fusion ART unifies a number of important neural models developed over the past decades, including Adaptive Resonance Theory (ART) networks for unsupervised learning, Adaptive Resonance Associative Map (ARAM) for supervised learning, and Fusion Architecture for Learning and Cognition (FALCON) for reinforcement learning. Following the notion of embodied cognition, fusion ART, encompassing a set of universal neural coding and adaptation principles, can be used as a building block for cognitive computation and intelligent behaviours, notably real-time reinforcement learning, reasoning, and decision making. In this talk, case studies will be presented, illustrating how such cognitive systems may be manifested as Non-Player Characters (NPC) in virtual game environment and Computer Generated Forces (CGF) in combat simulation.
Bio: Dr Ah-Hwee Tan received Ph.D. in Cognitive and Neural Systems from Boston University, Master of Science and Bachelor of Science (First Class Honors) in Computer and Information Science from the National University of Singapore. He is currently Professor of Computer Science and Associate Dean (Research) at the School of Computing and Information Systems (SCIS), Singapore Management University (SMU). Before joining SMU, he was Professor of Computer Science at the School of Computer Science and Engineering (SCSE), Nanyang Technological University, where he last served as the Associate Chair (Research) of the school. Prior to NTU, he was a Senior Member of Research Staff at the A*STAR Institute for Infocomm Research (I2R), spearheading the Text Mining and Intelligent Agents research programmes. His current research interests include cognitive and neural systems, brain-inspired intelligent agents, machine learning, and text mining. Dr. Tan has published over 200 technical papers in major international journals and conferences of his fields, in addition to six edited books and proceedings. He holds two US patents, five Singapore patents, and has spearheaded several A*STAR projects in commercializing a suite of knowledge management and text mining software. He has served as Associate Editor/Editorial Board Member of several journals, including IEEE Transactions on Neural Networks and Learning, IEEE Transactions on SMC Systems, and IEEE Access. He is a Senior Member of IEEE, a Member of IEEE Computational Intelligent Society (CIS) Neural Networks Technical Committee (NNTC), Vice Chair of IEEE CIS Task Force on Towards Human-Like Intelligence, and General Co-Chair of 2022 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2022).
Metaverse Virtual Service Management: Game Theoretic Approaches
4 August 2022 | 2.00 p.m. – 3.00 p.m. (Singapore Time/ UTC+8)
Prof. Dusit (Tao) Niyato
Ph.D., IEEE Fellow, IET Fellow Professor
Nanyang Technological University
Abstract: Metaverse is the next-generation Internet after the web and the mobile network revolutions, in which humans (acting as digital avatars) can interact with other people and software applications in a three-dimensional (3D) virtual world. In this presentation, we first briefly introduce major concepts of Metaverse and the virtual service management. Then, we discuss applications of game theory in the virtual service management. First, we consider that virtual reality (VR) users in the wireless edge-empowered Metaverse can immerse themselves in the virtual through the access of VR services offered by different providers. The VR service providers (SPs) have to optimize the VR service delivery efficiently and economically given their limited communication and computation resources. An incentive mechanism can be thus applied as an effective tool for managing VR services between providers and users. Therefore, we propose a learning-based incentive mechanism framework for VR services in the Metaverse. Second, we consider virtual services provided through the digital twin, i.e., a digital replication of real-world entities in the Metaverse. The real-world data collected by IoT devices and sensors are key for synchronizing the two worlds. A group of IoT devices are employed by the Metaverse platform to collect such data on behalf of virtual service providers (VSPs). Device owners, who are self-interested, dynamically select a VSP to maximize rewards. We adopt hybrid evolutionary dynamics, in which heterogeneous device owner populations can employ different revision protocols to update their strategies. To this end, we discuss some important research directions in Metaverse virtual service management.
Bio: Dusit Niyato is currently a professor in the School of Computer Science and Engineering, Nanyang Technological University, Singapore. He received B.E. from King Mongkuk’s Institute of Technology Ladkrabang (KMITL), Thailand in 1999 and Ph.D. in Electrical and Computer Engineering from the University of Manitoba, Canada in 2008. Dusit's research interests are in the areas of distributed collaborative machine learning, Internet of Things (IoT), edge intelligent metaverse, mobile and distributed computing, and wireless networks. Dusit won the Best Young Researcher Award of IEEE Communications Society (ComSoc) Asia Pacific and The 2011 IEEE Communications Society Fred W. Ellersick Prize Paper Award and the IEEE Computer Society Middle Career Researcher Award for Excellence in Scalable Computing in 2021 and Distinguished Technical Achievement Recognition Award of IEEE ComSoc Technical Committee on Green Communications and Computing 2022. Dusit also won a number of best paper awards including IEEE Wireless Communications and Networking Conference (WCNC), IEEE International Conference on Communications (ICC), IEEE ComSoc Communication Systems Integration and Modelling Technical Committee and IEEE ComSoc Signal Processing and Computing for Communications Technical Committee 2021. Currently, Dusit is serving as Editor-in-Chief of IEEE Communications Surveys and Tutorials, an area editor of IEEE Transactions on Vehicular Technology, editor of IEEE Transactions on Wireless Communications, associate editor of IEEE Internet of Things Journal, IEEE Transactions on Mobile Computing, IEEE Wireless Communications, IEEE Network, and ACM Computing Surveys. He was a guest editor of IEEE Journal on Selected Areas on Communications. He was a Distinguished Lecturer of the IEEE Communications Society for 2016-2017. He was named the 2017-2021 highly cited researcher in computer science. He is a Fellow of IEEE and a Fellow of IET.
Recent Progress in Large Vocabulary Continuous Speech Recognition
4 August 2022 | 4.00 p.m. – 5.00 p.m. (Singapore Time/ UTC+8)
Prof. Chng Eng Siong
Nanyang Technological University
Abstract: Modern Speech recognition has a long history, stretching from the 70s. It received renewed interest and significant improvement in recognition performance due to the injection of DNN approaches into its acoustic modelling abilities in 2013, and lately transformed itself from the traditional Acoustic + Language + Decoder approach to an end-to-end system which has almost reached state of the art performance.
In this talk, we will share our experience in developing codes-switching English/ Mandarin speech recognition in two widely used systems to develop speech recognition engines and highlight existing problems remaining.
Bio: Dr Chng Eng Siong is currently an Associate Professor in the School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU), Singapore. Prior to joining NTU in 2003, he has worked in several research centers/companies, namely: Knowles Electronics (USA), Lernout and Hauspie (Belgium), Institute of Infocomm Research (I2R, Singapore), and RIKEN (Japan) with focus in signal processing and speech research. He received both PhD and BEng (Hons) from Edinburgh University, U.K. in 1996 and 1991 respectively. His research current focus on: speech recognition using DNN frameworks, low resource, noisy conditions and adaptation to target domains (accent, use-cases). Additionally, he explores multilingual code-switch speech recognition such as: English/Mandarin, and English/Malay.
To date, he has been Principal Investigator of research grants awarded by Alibaba, NTU-Rolls Royce, Mindef, MOE and AStar with a total funding amount of over S$10 million under the “Speech and Language Technology Program (SLTP)” at SCSE. He has graduated 17 PhD students and 10 Masters Engineering students. His publications include 2 edited books and over 100 journal/conference papers. He has served as the publication chair for 5 international conferences (Human Agent Interaction 2016, INTERSPEECH 2014, APSIPA-2010, APSIPA-2011, ISCSLP-2006) and local organizing committee in ASRU 2019.