Dr Yubiao Sun is a Newton International Fellow at the University of Cambridge. He obtained his PhD in Mechanical Engineering from the University of Queensland, followed by postdoctoral research at the National University of Singapore. His research intersects machine learning, heat and mass transfer, renewable energy conversion and nanotechnology. He has conducted multiple interdisciplinary research programs to evaluate, understand, and control the physical mechanisms governing the multiphase flows, accumulating experience and expertise in both theoretical and experimental research areas. His current work combines machine learning with the fundamentals of fluid mechanics to optimize existing designs for various applications. His work was published in 28 peer-reviewed papers, 2 patents, 1 book chapter, 6 conference proceedings as well as 9 invited talks. He also served as the guest editor of two special issues for Energies and Symmetry.

Luca Oneto was born in Rapallo, Italy in 1986. He received his BSc and MSc in Electronic Engineering at the University of Genoa, Italy respectively in 2008 and 2010. In 2014 he received his PhD from the same university in the School of Sciences and Technologies for Knowledge and Information Retrieval with the thesis "Learning Based On Empirical Data". In 2017 he obtained the Italian National Scientific Qualification for the role of Associate Professor in Computer Engineering and in 2018 he obtained the one in Computer Science. He worked as Assistant Professor in Computer Engineering at University of Genoa from 2016 to 2019. In 2018 he was co-funder of the spin-off ZenaByte s.r.l. In 2019 he obtained the Italian National Scientific Qualification for the role of Full Professor in Computer Science and Computer Engineering. In 2019 he became Associate Professor in Computer Science at University of Pisa and currently is Associate Professor in Computer Engineering at University of Genoa. He has been involved in several H2020 projects (S2RJU, ICT, DS) and he has been awarded with the Amazon AWS Machine Learning and Somalvico (best Italian young AI researcher) Awards. His first main topic of research is the Statistical Learning Theory with particular focus on the theoretical aspects of the problems of (Semi) Supervised Model Selection and Error Estimation. His second main topic of research is Data Science with particular reference to the problem of Trustworthy AI and the solution of real world problems by exploiting and improving the most recent Learning Algorithms and Theoretical Results in the fields of Machine Learning and Data Mining.

Deep Learning models have nowadays matched, if not surpassed, the human ability of solving specific tasks (e.g., cancer skin detection, playing the go game, and solving protein folding problem) becoming a commodity in many applications by means of MLaaS and then impacting society at large. For this reason, the trustworthiness of Deep Learning models, namely their ability to meet both technical (e.g., performance, computational requirements, and non regressivity) and human-related (e.g., fairness, robustness, privacy, and explainability) requirements, is now becoming crucial and questioned by society, regulatory bodies, and researchers. This talk focuses on this fundamental problem bridging the gap between practice (i.e., empirical evidence of trustworthiness problems) and theory (i.e., the theoretical explanations behind such problems) depicting the current solutions and the open challenges of this important field of research.

PDE-constrained optimization is an exceedingly difficult task due to the curse of dimensionality. This is particularly true in aerodynamics optimization as remeshing or deformation of existing meshes is often required. In this paper, we aim to overcome this challenge by proposing a physics-based machine learning framework that can handle complex optimization problems efficiently. The proposed approach is able to simultaneous make predictions and perform optimizations. Specifically, the framework consists of a surrogate model to generate high-fidelity solutions and a gradient-based algorithm to address high-dimensional optimization problems. The starting point is to use physics-informed neural network (PINN) to construct surrogate models that output flow fields for airfoils of varied configurations. In this sense, PINN is computationally cheap as no labelled training data from a separate high-fidelity simulation is required. Thus, a trained surrogate model can efficiently generate flow fields for any intermediate optimization scenarios. More importantly, we design the architecture of surrogate models and include design variables as inputs to PINN. This mechanism enables neural network to extract geometric features of various input computational domains. A trained surrogate model can represent solutions on unseen design cases from both seen and unseen categories. In the optimization process, a quasi-Newton algorithm is used and further accelerated by automatic differentiation, a popular algorithm designed to efficiently compute the gradients of objective functions with respect to design parameters. An optimization examples aiming to achieve the maximal lift-to-drag ratio has been presented. The example is a single parameter optimization problem focusing on finding the optimal angle of attack. The proposed method is straightforward to implement and computationally efficient, providing a promising alternative for computationally intensive optimization problems.

Daniel Polani is Professor of Artificial Intelligence, Director of the Centre for Computer Science and Informatics Research (CCSIR) and Head of the Adaptive Systems Research Group at the School of Physics, Engineering and Computer Science at the University of Hertfordshire.
His research interests include the emergence of life, cognition, intelligence and robotics from first, especially information-theoretic, principles. Ramifications of this research range from practical applications to more fundamental questions, such as the role of embodiment, intrinsic motivations and taskless utilities, to questions from cognitive science, psychology, social science, and biology.

We investigate the relation between information (in the Shannon sense) and decision-making. It turns out that information is a prime resource for any agent or robot. Taking this into account permits one to formulate principles of arranging information in the decision-making process of such an agent. Thus, the necessities of information processing imply certain types of invariants and architectures - or also principles by which behaviour should naturally be selected.
This has ramifications for the organization of the sensorimotor loop and, by implication, sensorics and actuatorics and behaviours. My talk will discuss a number of scenarios illustrating these points.

Ruhul A Sarker obtained his PhD from Dalhousie University (former TUNS), Halifax, Canada in 1992. He is currently a senior Professor in the School of Engineering and IT (SEIT) at the University of New South Wales, Canberra campus (UNSW Canberra). Prof. Sarker’s broad research interests are decision analytics, CI / evolutionary computation, and applied optimization with an emphasis on Augmenting Human Intelligence (AHI). He has received numerous awards from international conferences, algorithm competitions and professional bodies. His name appeared on the lists of top 2% of world's scientists-researchers published by Stanford University and also Elsevier /Scopus /digitalcommonsdata. Prof. Sarker has published more than 400 papers in the top journals and conferences in his areas of research. As of Google Scholar, his papers were cited more than 11,500 times and his current h-index is 55. He has been invited to deliver keynote speech in many international conferences including IEEE WCCI 2020. Prof. Sarker has successfully obtained more than A$5 million external research grants. He is the lead author of the bookOptimization Modelling: A Practical Approach, Taylor & Francis /CRC Press, Boca Raton. Currently, he is an associate editor of three international journals.

Combinatorial problem-solving is an old field of study. However, it has always been a significant research topic because of its importance in theory and practice. In the past, conventional approaches were the core of combinatorial problem-solving. Over the last few decades, Computational Intelligence (CI) has become popular for solving such problems. CI techniques augment human problem-solving logic (/intelligence) using computational power. Recently, the configuration of CI-based algorithms for solving combinatorial problems has become an emerging research topic. In this talk, we will discuss some specific CI-based approaches and their contributions to the real-world combinatorial problem-solving domain. In addition, we will share our experiences with some practical issues in problem environments, and their solution approaches.

G. Kumar Venayagamoorthy is the Duke Energy Distinguished Professor of Power Engineering and Professor of Electrical and Computer Engineering at Clemson University since January 2012. Prior to that, he was a Professor of Electrical and Computer Engineering at the Missouri University of Science and Technology (Missouri S&T), Rolla, USA where he was from 2002 to 2011. Dr. Venayagamoorthy was a Senior Lecturer in Department of Electronic Engineering, Durban University of Technology, Durban, South Africa, where he was from 1996 to 2002. He was the BTech and MTech program coordinator for the Electronic Engineering Dept. and the Chair of Faculty of Engineering Research Committee.
Dr. Venayagamoorthy is the Founder and Director of the Real-Time Power and Intelligent Systems Laboratory at Missouri S&T and Clemson University. Dr. Venayagamoorthy received his PhD and MScEng degrees in Electrical Engineering from the University of Natal, Durban, South Africa. He received his BEng degree with a First-Class Honors in Electrical and Electronics Engineering from Abubakar Tafawa Balewa University, Bauchi, Nigeria. He holds an MBA degree in Entrepreneurship and Innovation from Clemson University, USA.
Dr. Venayagamoorthy’s interests are in research, development and innovation of smart grid and artificial intelligence technologies. He is a 2004 US NSF CAREER Awardee, a 2007 US Office of the Naval Research (ONR) Young Investigator Program (YIP) Awardee, and a 2008 NSF Emerging Frontiers in Research and Innovation (EFRI) Awardee. He led the brain2grid project funded by US National Science Foundation (NSF). Dr. Venayagamoorthy is an inventor of technologies for scalable computational intelligence for complex systems and dynamic stochastic optimal power flow. He has published over 550 refereed technical articles which are cited ~ 22,000 times with a h-index of 70 and i10-index of > 300. Dr. Venayagamoorthy has given over 500 invited technical presentations including keynotes and plenaries in over 40 countries to date.
Dr. Venayagamoorthy is involved in the leadership and organization of conferences including the Clemson University Power System Conference and Pioneer and Founder and Chair/co-Chair of the IEEE Symposium of Computational Intelligence Applications in Smart Grid (CIASG). He is currently the Chair of the IEEE PES Working Group on Intelligent Control Systems, and the Founder and Chair of IEEE Computational Intelligence Society (CIS) Task Force on Smart Grid. He has served/serves as Editor/Associate Editor/Guest Editor of several IEEE Transactions and Elsevier Journals. He is the Editor for the IEEE Press Series on Power and Energy Systems.
Dr. Venayagamoorthy has received several awards for faculty, research and teaching excellence from universities, professional societies, and organizations. Dr. Venayagamoorthy is a Fellow of the IEEE, IET (UK), the South African Institute of Electrical Engineers (SAIEE) and Asia-Pacific Artificial Intelligence Association (AAIA), and a Senior Member of the International Neural Network Society. According to Elsevier BV, Dr. Venayagamoorthy has been ranked in 2019, 2020 and 2021 among the Top 25,000 scientists worldwide across all fields and in the top 0.1% worldwide in the fields of energy and AI.

Combinatorial problem-solving is an old field of study. However, it has always been a significant research topic because of its importance in theory and practice. In the past, conventional approaches were the core of combinatorial problem-solving. Over the last few decades, Computational Intelligence (CI) has become popular for solving such problems. CI techniques augment human problem-solving logic (/intelligence) using computational power. Recently, the configuration of CI-based algorithms for solving combinatorial problems has become an emerging research topic. In this talk, we will discuss some specific CI-based approaches and their contributions to the real-world combinatorial problem-solving domain. In addition, we will share our experiences with some practical issues in problem environments, and their solution approaches.

Donald C. Wunsch II (F 05) is the Mary K. Finley Missouri Distinguished Professor at Missouri University of Science and Technology (Missouri S&T), Rolla, Missouri. He is the Director of the Kummer Institute Center for Artificial Intelligence and Autonomous Systems at Missouri S&T and Director of the Applied Computational Intelligence Laboratory. Earlier employers were: Texas Tech (Lubbock, TX,) Boeing (Seattle, WA,) Rockwell International (Albuquerque, NM,) and International Laser Systems, (Albuquerque, NM). His education includes: Ph.D., Electrical Engineering - University of Washington (Seattle, WA), M.B.A. - Washington University (St. Louis, MO), M.S., Applied Mathematics - University of Washington (Seattle, WA), B.S., Applied Mathematics - University of New Mexico (Albuquerque, NM), Jesuit Honors Program, Seattle University (Seattle, WA) and Kellogg Graduate Certificate in Nonprofit Management, Northwestern University (Evanston, IL). Research interests include real-time learning, Unsupervised Learning, Reinforcement Learning and their applications. Awards include: IEEE Fellow, International Neural Networks Society (INNS) Fellow, NSF CAREER, INNS Gabor Award, INNS Ada Lovelace Award, and IEEE Neural Networks Pioneer Award. He served as INNS President, IJCNN General Chair, and on the St. Patrick’s School Board, IEEE Neural Networks Council, INNS Board, and the University of Missouri Bioinformatics Consortium, chaired the Missouri S&T Information Technology and Computing Committee and the Student Design and Experiential Learning Center Board. He also served as a Program Director at the National Science Foundation 2021 - 2022. He produced 23 Ph.D. recipients in Computer Engineering, Electrical Engineering, Systems Engineering and Computer Science.

Unsupervised learning has continued to be a frontier of neural networks and machine learning research for decades, due to its fundamental challenges. A core challenge is evaluating the quality of results, which has resulted in many quality measures known as cluster validity indices (CVIs). Recently, it has been recognized that CVIs can be computed much more efficiently while maintining their utility, an approach known as incremental cluster validity indices (iCVIs). This presentation will explain about the development of iCVIs and how they can be used to improve results in practice. The use of iCVIs is recommended for most unsupervised learning problems regardless of one’s preferred clustering technique. There is also a potential to employ them in combination with other machine learning techniques beyond unsupervised learning.