Department of Computer Science CINVESTAV-IPN, Mexico
Fellow IEEE, Editor-in-Chief, IEEE Transactions on Evolutionary Computation

Dr. Carlos Coello is Professor with Distinction (Investigador CINVESTAV 3F) at the Center for Research and Advanced Studies of the Instituto Politécnico Nacional (CINVESTAV-IPN) in Mexico City and Visiting Professor at the Basque Center for Applied Mathematics in Spain. Has taught master's and Ph.D. level courses on evolutionary computation, evolutionary multi-objective optimization, programming languages, and engineering optimization at CINVESTAV-IPN. In addition, he has taught short courses in Spain, England, Argentina, Chile, India, Bolivia, Colombia, Slovenia, and the USA. Also, Professor Coello has presented scientific articles at major conferences specialized in evolutionary computation, like the IEEE Congress on Evolutionary Computation (CEC), the Genetic and Evolutionary Computation Conference (GECCO), Parallel Problem Solving from Nature (PPSN), and others. His work and research fall at the intersection of computer science, applied mathematics, and operations research. His main contributions have revolved around the design of biologically inspired stochastic algorithms to solve highly complex multi-objective optimization problems (mainly non-linear). He has made pioneering contributions to this area which is now known as multi-objective evolutionary optimization. For example, he proposed, along with his research group, the first genetic micro-algorithm for multi-objective optimization, which has been used in real-world applications in various countries like the United States for the design of supersonic business jets. Also, the first algorithm for multi-objective optimization based on an artificial immune system incorporating the concept of Pareto optimality, which has been a reference in specialized literature used to validate new multi-objective algorithms. Dr. Coello has broad experience as an expert consultant in his field. He is a Member of the Foundation Advisory Board of The International AIQT Foundation, which strives to establish a highly competitive (international-level) research center in artificial intelligence and quantum technology. He is also Scientific Advisor of the company Complexica, in Australia, and was Senior Advisor of the Hunan Zixing AI Research Institute from China (2017-2020), to name some examples. His research interests revolve around the areas of evolutionary computation (genetic algorithms and evolution strategies), as well as engineering optimization. In addition, he has worked on over 12 funded research projects, the most recent one called ‘Alternative Selection Schemes for Multi-Objective Evolutionary Algorithms’ funded by CONACYT, in which he was Principal Investigator. Dr. Coello has collaborated as an Associate Editor in multiple international journals like the IEEE Transactions on Evolutionary Computation, Evolutionary Computation (the MIT Press), Journal of Heuristics (Springer), Computational Optimization and Applications (Springer), Pattern Analysis and Applications (Springer), to name a few. He is currently Editor-in-Chief of the IEEE Transactions on Evolutionary Computation journal.

 

Speech Title: Some Challenges in Evolutionary Multi-Objective Optimization

Abstract: In this talk, after providing a very short introduction to evolutionary multi-objective optimization, some of its　current research challenges will be briefly described, including diversity measures, large-scale problems, expensive objectives and constraints, parallelism and algorithmic design. Also, a discussion on the importance of advancing the field with more disruptive ideas rather than just doing research by analogy will be also emphasized.

 

Simon Fraser University, Canada
Fellow IEEE, Editor-in-Chief, IEEE Transactions on Human-Machine Systems
Past President, IEEE Systems, Man, and Cybernetics Society and IEEE Circuits and Systems Society

Ljiljana Trajkovic received the Dipl. Ing. degree from University of Pristina, Yugoslavia, in 1974, the M.Sc. degrees in electrical engineering and computer engineering from Syracuse University, Syracuse, NY, in 1979 and 1981, respectively, and the Ph.D. degree in electrical engineering from University of California at Los Angeles, in 1986. She is currently a Professor in the School of Engineering Science at Simon Fraser University, Burnaby, British Columbia, Canada. From 1995 to 1997, she was a National Science Foundation (NSF) Visiting Professor in the Electrical Engineering and Computer Sciences Department, University of California, Berkeley. She was a Research Scientist at Bell Communications Research, Morristown, NJ, from 1990 to 1997, and a Member of the Technical Staff at AT&T Bell Laboratories, Murray Hill, NJ, from 1988 to 1990. Her research interests include communication networks, computer-aided circuit analysis and design, and nonlinear circuits and dynamical systems. Dr. Trajkovic served as IEEE Division X Delegate/Director (2019–2020) and IEEE Division X Delegate-Elect/Director-Elect (2018). She served as Senior Past President (2018–2019), Junior Past President (2016–2017), President (2014–2015), President-Elect (2013), Vice President Publications (2012–2013, 2010–2011), Vice President Long-Range Planning and Finance (2008–2009), and a Member at Large of the Board of Governors (2004–2006) of the IEEE Systems, Man, and Cybernetics Society. She served as 2007 President of the IEEE Circuits and Systems Society and a member of its Board of Governors (2004–2005, 2001–2003). She served as Chair of the IEEE Circuits and Systems Society joint Chapter of the Vancouver/Victoria Sections (2001–2021). She was Chair of the IEEE Technical Committee on Nonlinear Circuits and Systems (1998). She was General Co-Chair of SMC 2020 and General Co-Chair of SMC 2020, SMC 2019, and SMC 2018 Workshops on BMI Systems, SMC 2016, and HPSR 2014, Special Sessions Co-Chair of SMC 2017, Technical Program Chair of SMC 2017 and SMC 2016 Workshops on BMI Systems, Technical Program Co-Chair of ISCAS 2005, and Technical Program Chair and Vice General Co-Chair of ISCAS 2004. She serves as Editor-in-Chief of the IEEE Transactions on Human-Machine Systems (2021–2023) and served as an Associate Editor of the IEEE Transactions on Circuits and Systems (Part I) (2004–2005, 1993–1995), the IEEE Transactions on Circuits and Systems (Part II) (2018, 2002–2003, 1999–2001), and the IEEE Circuits and Systems Magazine (2001–2003). She is a Distinguished Lecturer of the IEEE Systems, Man, and Cybernetics Society (2020–2021) and the IEEE Circuits and Systems Society (2020–2021, 2010–2011, 2002–2003). She is a Professional Member of IEEE-HKN and a Life Fellow of the IEEE.

 

Speech Title: Machine Learning for Detecting Internet Traffic Anomalies

Abstract: Border Gateway Protocol (BGP) enables the Internet data routing. BGP anomalies may affect the Internet connectivity and cause routing disconnections, route flaps, and oscillations. Hence, detection of anomalous BGP routing dynamics is a topic of great interest in cybersecurity. Various anomaly and intrusion detection approaches based on machine learning have been employed to analyze BGP update messages collected from RIPE and Route Views collection sites. Survey of supervised and semi-supervised machine learning algorithms for detecting BGP anomalies and intrusions is presented. Deep learning, broad learning, gradient boosting decision tree, and reservoir computing algorithms are evaluated by developing models based on collected datasets that contain Internet worms, power outages, and ransomware events.

 

Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil
Secretary, International Neural Network Society, Vice President (Conferences), IEEE Computational Intelligence Society

Marley Maria Bernardes Rebuzzi Vellasco is a Full Professor at the Electrical Engineering Department of the Pontifical Catholic University of Rio de Janeiro (PUC-Rio), which she joined in 1989. She received the BSc and MSc degrees in Electrical Engineering from the Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil, in 1984 and 1987, respectively, and the PhD degree in Computer Science from the University College London (UCL) in 1992. She has published more than 80 papers in professional journals and more than 400 papers in conference proceedings. She is also the author of 5 books and 18 book chapters in the area of soft computing. She has supervised more than 40 PhD Thesis and 90 MSc Dissertations. She is currently a member of the CNPq Computer Science Advisory Committee and acts as Associate Editor of the main journals in the Computational Intelligence area, such as Neural Networks, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Fuzzy Systems, IEEE Transactions on Artificial Intelligence, IEEE Transactions on Cognitive and Developmental Systems, and Engineering Applications of Artificial Intelligence. Prof. Vellasco has served on the Board of Governors of the International Neural Network Society for three consecutive terms (2011 to 2019) and is currently the Secretary of the INNS. She also serves as Vice-President for Conferences of the IEEE Computational Intelligence Society (CIS) since 2020. Since 1991, she has coordinated more than 50 research projects, including international cooperation projects. She is the coordinator of the Centre of Artificial Intelligence in Rio de Janeiro (CIA-Rio), sponsored by FAPERJ. She has experience in the areas of Electrical Engineering and Computer Science, with an emphasis on Computational Intelligence, working mainly on the following topics: neural networks, fuzzy logic and evolutionary computing, focusing on developing intelligent hybrid systems for AutoML (Automatic Machine Learning), such as neuro-evolutionary, fuzzy-evolutionary and neural architecture search (NAS) models.

 

Speech Title: Quantum-inspired Evolutionary Algorithm Applied to Neural Architecture Search

Abstract: The area of ​​automatic machine learning (AutoML) aims to develop decision support systems automatically. The goal is to make machine learning accessible to other scientists who want to apply these techniques to their domains. The area of ​​neuro-evolutionary models or, more recently, Neural Architecture Search (NAS) can be seen as a sub-area of ​​AutoML and is an essential step towards automating the development of neural network architectures. This talk presents an overview of quantum-inspired evolutionary models and their application in the automatic evolution of different models of artificial neural networks, from simple (shallow) Multi-Layer Perceptrons and Recurrent Neural Networks to more complex deep Convolutional Neural Networks.