Title: Multi-modal and Uncertain Optimization with Differential Evolution - Some Recent Approaches and Future Challenges.
by Professor Swagatam Das, India Institute of Technology https://www.isical.ac.in/~swagatam.das/
Abstract: Differential Evolution (DE) is arguably one of the most powerful stochastic real-parameter optimization algorithms of current interest. DE operates through similar computational steps as employed by a standard Evolutionary Algorithm (EA). However, unlike traditional EAs, the DE variants perturb the current-generation population members with the scaled differences of distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance. This talk will begin with a brief but comprehensive overview of the basic concepts related to DE, its algorithmic components and control parameters. It will subsequently discuss some of the significant algorithmic variants of DE for bound-constrained single-objective optimization for high-dimensional search spaces. The talk will then focus on some interesting DE variants with additional mechanisms like a distance-based selection, a clustering procedure and aging mechanisms for optimization of objective functions corrupted with additive noise from various sources (with various probability distributions) and also optimization over dynamic/noisy fitness landscapes where the optima can shift with time. The talk will finally discuss a few interesting applications of DE and highlight a few open research problems.
Bio: Swagatam Das is currently serving as an associate professor at the Electronics and Communication Sciences Unit of the Indian Statistical Institute, Kolkata, India. His research interests include evolutionary computing, pattern recognition, multi-agent systems, and wireless communication. Dr. Das has published one research monograph, one edited volume, and more than 200 research articles in peer-reviewed journals and international conferences. He is the founding co-editor-in-chief of Swarm and Evolutionary Computation, an international journal from Elsevier. He has also served as or is serving as the associate editors of Pattern Recognition (Elsevier), IEEE Trans. on Systems, Man, and Cybernetics: Systems, IEEE Computational Intelligence Magazine, IEEE Access, Neurocomputing (Elsevier), Engineering Applications of Artificial Intelligence (Elsevier), and Information Sciences (Elsevier). He is an editorial board member of Progress in Artificial Intelligence (Springer), PeerJ Computer Science, International Journal of Artificial Intelligence and Soft Computing, and International Journal of Adaptive and Autonomous Communication Systems. Dr. Das has 14000+ Google Scholar citations and an H-index of 56 till date. He has been associated with the international program committees and organizing committees of several regular international conferences including IEEE CEC, IEEE SSCI, SEAL, GECCO, and SEMCCO. He has acted as guest editors for special issues in journals like IEEE Transactions on Evolutionary Computation and IEEE Transactions on SMC, Part C. He is the recipient of the 2012 Young Engineer Award from the Indian National Academy of Engineering (INAE). He is also the recipient of the 2015 Thomson Reuters Research Excellence India Citation Award as the highest cited researcher from India in Engineering and Computer Science category between 2010 to 2014.
Talk (2) Modern Algorithms in Control and Design of Complex Systems
By Professor Ivan Zelinka
Department of Computer Science, Faculty of Electrical Engineering and Computer Science VŠB-TUO
This keynote discusses the mutual intersection of exciting fields of research: bio-inspired algorithms, deterministic chaos and complex systems. The first one will discuss main principles of bio-inspired methods, its historical background and its use on various examples including real-world ones. Examples include plasma reactor control, optimal signal routing in the network of portable meteorological stations, complex system design as antenna design, nonlinear system and controllers design and more. Also, its use in deterministic chaos control with focusing on simple chaotic systems (logistic, Hennon,…), as well as CML systems exhibiting spatiotemporal chaos, will be mentioned and explained. The second part will discuss the use of deterministic chaos instead of pseudo-random number generators inside evolutionary algorithms with the application on well known evolutionary algorithms (differential evolution, PSO, SOMA, genetic algorithms,..) and test functions. A mutual comparison will be presented, based on our research. Also will be discussed the question whether evolutionary dynamics need pseudo-random numbers or no. At the end will be mentioned a novel approach joining evolutionary dynamics, complex networks and CML systems exhibiting chaotic behaviour. Reported methodology and results are based on the actual state of the art (that is a part of this keynote) as well as on our research. The keynote is designed as an introduction; no advanced or expert knowledge from complex networks, chaos and control is expected.
Bio: Ivan Zelinka is currently working at the Technical University of Ostrava (VSB-TU), Faculty of Electrical Engineering and Computer Science. He graduated consequently at Technical University in Brno (1995 – MSc.), UTB in Zlin (2001 – PhD) and again at Technical University in Brno (2004 – assoc. prof.) and VSB-TU (2010 - professor). Before academic career, he was an employed like TELECOM technician, computer specialist (HW+SW) and Commercial Bank (computer and LAN supervisor). During his career at UTB, he proposed and opened 7 different lectures. He also has been invited for lectures at numerous universities in different EU countries plus the role of the keynote speaker at the Global Conference on Power, Control and Optimization in Bali, Indonesia (2009), Interdisciplinary Symposium on Complex Systems (2011), Halkidiki, Greece and IWCFTA 2012, Dalian China. The field of his expertise if mainly on unconventional algorithms and cybersecurity. He is and was responsible supervisor of 3 grant of fundamental research of Czech grant agency GAČR, co-supervisor of grant FRVŠ - Laboratory of parallel computing. He was also working on numerous grants and two EU project like a member of the team (FP5 - RESTORM) and supervisor (FP7 - PROMOEVO) of the Czech team and supervisor of international research (founded by TACR agency) focused on the security of mobile devices (Czech - Vietnam). Currently, he is a professor at the Department of Computer Science and in total, he has been the supervisor of more than 40 MSc. and 25 Bc. diploma thesis. Ivan Zelinka is also supervisor of doctoral students including students from the abroad. He was awarded by Siemens Award for his PhD thesis, as well as by journal Software news for his book about artificial intelligence. Ivan Zelinka is a member of British Computer Society, Editor in chief of Springer book series: Emergence, Complexity and Computation (http://www.springer.com/series/10624), Editorial board of Saint Petersburg State University Studies in Mathematics, a few international program committees of various conferences and international journals. He is the author of journal articles as well as of books in Czech and English language and one of three founders of TC IEEE on big data http://ieeesmc.org/about-smcs/history/2014-archives/44-about-smcs/history/2014/technical-committees/204-big-data-computing/ . He is also head of research group NAVY http://navy.cs.vsb.cz.
Hands-on to TensorFlow
Abstract: TensorFlow is an open source software library for numerical computation using data and flow graphs. In this tutorial, you will be introduced to TensorFlow and how to use for training deep learning models using CPU and GPU. You will learn how to use colab notebooks with real-world examples.
Speaker: Ibrahim A. Hameed has a Ph.D. in artificial intelligence from South Korea.
A Ph.D. in field robotics from Denmark. He is working as an Associate Professor at the department of ICT at the Norwegian University of Science and Technology, Noway. He is a deputy head of research and innovation. He is the head of the international master program in Simulation and Innovation.