IEEE CIS Lecture Series on Contemporary Advancements in Computational Intelligence (CACI)
Contemporary Advancements in Computational Intelligence (CACI)
Date and Time
Location
Hosts
Registration
- Date: 13 Jun 2025
- Time: 12:30 PM UTC to 05:30 PM UTC
-
Add Event to Calendar
- Starts 30 May 2025 03:06 AM UTC
- Ends 11 June 2025 06:25 PM UTC
- No Admission Charge
Speakers
Prof. Suganthan of Qatar University
Randomization Based Deep and Shallow Learning Methods for Classification and Forecasting
Abstract: This talk will first introduce the main randomization-based feedforward learning paradigms with closed-form solutions. The popular instantiation of the feedforward neural networks is called random vector functional link neural network (RVFL). Other feedforward methods included in the presentation are random weight neural networks (RWNN), extreme learning machines (ELM), Stochastic Configuration Networks (SCN), and Broad Learning Systems (BLS). We will also present deep random vector functional link implementations. Hyperparameter tuning will be addressed in detail. The talk will also present extensive benchmarking studies using classification and forecasting datasets.
Biography:
Ponnuthurai Nagaratnam Suganthan received the B.A degree and M.A degree in Electrical and Information Engineering from the University of Cambridge, UK in 1990, and 1994, respectively. He received an honorary doctorate (i.e. Doctor Honoris Causa) in 2020 from University of Maribor, Slovenia. After completing his PhD research in 1995, he served as a pre-doctoral Research Assistant in the Dept of Electrical Engineering, University of Sydney in 1995–96 and a lecturer in the Dept of Computer Science and Electrical Engineering, University of Queensland in 1996–99. Since August 2022, he has been with KINDI Computing Research, Qatar University, as a research professor. He was an Editorial Board Member of the Evolutionary Computation Journal, MIT Press (2013-2018). He is/was an associate editor of the Applied Soft Computing (Elsevier, 2018-), Neurocomputing (Elsevier, 2018-), IEEE Trans on Cybernetics (2012 - 2018), IEEE Trans on Evolutionary Computation (2005 - 2021), Information Sciences (Elsevier) (2009 - ), Pattern Recognition (Elsevier) (2001 - ) and IEEE Trans on SMC: Systems (2020 - ) Journals. He is a founding co-editor-in-chief of Swarm and Evolutionary Computation (2010 - 2023), an SCI Indexed Elsevier Journal. He is a co-Editor-in-Chief of Computers and Electrical Engineering (2024- ), an SCI-indexed Elsevier journal. His co-authored SaDE paper (published in April 2009) won the "IEEE Trans. on Evolutionary Computation outstanding paper award" in 2012. His research interests include randomization-based learning methods, swarm and evolutionary algorithms, pattern recognition, deep learning and applications of swarm, evolutionary & machine learning algorithms. He was selected as one of the highly cited researchers by Thomson Reuters Science Citation yearly from 2015 to 2023 in computer science. He served as the General Chair of the IEEE SSCI 2013. He has been a member of the IEEE (S'91, M'92, SM'00, Fellow 2015) since 1991 and an elected AdCom member of the IEEE Computational Intelligence Society (CIS) in 2014-2016. He was an IEEE CIS distinguished lecturer (DLP) in 2018-2021.
Email:
Address:Qatar
Prof. Hillol of Agnik International Pvt. Ltd.
Distributed Machine Learning for Scalable Artificial Intelligence: Algorithms and Applications
Machine learning is playing an increasingly important role in reshaping this world through intelligent adaptive AI-powered applications. Learning large models from massive amount of data requires scalable high-performance machine learning algorithms that are suitable for quasi-decomposable distributed computing environments. This talk will start by giving an overview of the field of distributed machine
learning --- its history, current state of the art, and the challenges. It will focus on algorithms that pay attention to provable correctness in addition to computational and communication efficiency. The talk will consider model representations in distributed environments, their algebraic properties, and illustrate how scalable algorithms can be designed with careful attention to model and data representations in
distributed machine learning. It will conclude by identifying some of the ongoing large-scale applications and future directions.
Biography:
Dr. Hillol Kargupta is a co-founder and President of the Agnik Group of Companies. He is an IEEE Fellow.
He received his Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign in 1996.
He was a full Professor of Computer Science at the Univ. of Maryland, Baltimore County until 2014. Dr.
Kargupta won the 10-Year Highest Impact Paper Award from the IEEE Data Mining Conf. in 2013, IBM
Innovation Award in 2008, and NSF CAREER award in 2001. He and his team received the 2010 Frost and
Sullivan Enabling Tech. of the Year Award. Other awards include the 2016 Fleet Logistics Tech Outlook
Top-10 Fleet Management Solution Provider, CIO Review 2015 20 Most Promising Auto. Tech. Solution
Providers, best paper award for the 2003 IEEE Int. Conf. on Data Mining for a paper on privacy-preserving
data mining, the 2000 TRW Foundation Award, and the 1997 Los Alamos Award for Outstanding
Technical Achievement. His dissertation earned him the 1996 Society for Industrial and Applied
Mathematics annual best student paper prize. He published more than one hundred peer-reviewed
articles. His research has been funded by the NSF, US Air Force, US Dept. of Homeland Security, NASA,
DOT among others. He co-edited several books. He served as an associate editor of the IEEE Trans. on
Knowledge and Data Engg., IEEE Trans. on Systems, Man, and Cybernetics, Part B and Statistical Analysis
and Data Mining Journal. He was the Program Co-Chair of 2009 IEEE Int. Data Mining Conf., General
Chair of NGDM Symposiums, Prog. Co-Chair of 2005 SIAM Data Mining Conf. and Assoc. Gen. Chair of
the 2003 ACM SIGKDD Conference. (https://en.wikipedia.org/wiki/Hillol_Kargupta)
Email:
Address:United States