Prof. Marco GORI
University of Siena, Italy
Variational Laws of Learning
(6h lectures + 3h exercises)
By and large, most studies of machine learning and pattern recognition are rooted in the framework of statistics.This is primarily due to the way machine learning is traditionally posed, namely by a problem of extraction of regularities from samples of a probability distribution. This course promotes a truly different way of interpreting learning processes that relies on system dynamics. We promote a view of learning as the outcome of laws of nature that govern the interactions of intelligent agents with their own environment.We reinforce the underlying principle that the acquisition of cognitive skills by learning obeys information-based laws on these interactions, which hold regardless of biology. These laws are derived in a variational framework that is very much related to the principle of least action in physics, that is reformulated in a truly causal framework. A preliminary application to visual perception is given where the emergence of visual features is only driven by visual interactions with no supervision.
Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy, working partly at the School of Computer Science (McGill University, Montreal). In 1992, he became an Associate Professor of Computer Science at Università di Firenze and, in November 1995, he joint the Università di Siena, where he is currently full professor of computer science.
His main interests are in machine learning with applications to pattern recognition, Web mining, and game playing. He is especially interested in bridging logic and learning and in the connections between symbolic and sub-symbolic representation of information. He was the leader of the WebCrow project for automatic solving of crosswords, that outperformed human competitors in an official competition which took place during the ECAI-06 conference. As a follow up of this grand challenge he founded QuestIt, a spin-off company of the University of Siena, working in the field of question-answering. He is co-author of "Web Dragons: Inside the myths of search engines technologies", Morgan Kauffman (Elsevier), 2006, and “Machine Learning: A Constrained-Based Approach,” Morgan Kauffman (Elsevier), 2018.
Dr. Gori serves (has served) as an Associate Editor of a number of technical journals related to his areas of expertise, he has been the recipient of best paper awards, and keynote speakers in a number of international conferences. He was the Chairman of the Italian Chapter of the IEEE Computational Intelligence Society, and the President of the Italian Association for Artificial Intelligence. He is a fellow of the IEEE, ECCAI, IAPR. He is in the list of top Italian scientists kept by the VIA-Academy.
Prof. Alberto BEMPORAD
IMT School for Advanced Studies Lucca, Italy
Model predictive control
(6h lectures + 3h exercises)
Model Predictive Control (MPC) is a well-established technique for controlling multivariable systems subject to constraints on manipulated variables and outputs in an optimized way. Following a long history of success in the process industries, in recent years MPC is rapidly expanding in several other domains, such as in the automotive and aerospace industries, smart energy grids, and financial engineering. The course is intended for students and engineers who want to learn the theory and practice of Model Predictive Control (MPC) of constrained linear, linear time-varying, nonlinear, stochastic, and hybrid dynamical systems, and numerical optimization methods for the implementation of MPC. The course will make use of the MPC Toolbox for MATLAB developed by the teacher and co-workers (distributed by The MathWorks, Inc.) for basic linear MPC, and of the Hybrid Toolbox for explicit and hybrid MPC.
Alberto Bemporad was born in Florence on March 26, 1970. He received his master's degree in Electrical Engineering in 1993 and his Ph.D. in Control Engineering in 1997 from the University of Florence, Italy. He served in 1994/1995 as lieutenant in the Italian Army's Technical Corps in Rome, Italy. In 1996/97 he was with the Center for Robotics and Automation, Department of Systems Science & Mathematics, Washington University, St. Louis, USA. In 1997-1999 he held a postdoctoral position at the Automatic Control Laboratory, ETH Zurich, Switzerland, where he collaborated as a senior researcher until 2002. In 1999-2009 he was with the Department of Information Engineering of the University of Siena, Italy, becoming an associate professor in 2005. In 2010-2011 he was with the Department of Mechanical and Structural Engineering of the University of Trento, Italy. Since 2011 he is full professor at the IMT School for Advanced Studies Lucca, Italy, where he served as the director of the institute in 2012-2015. He spent visiting periods at Stanford University, University of Michigan, and Zhejiang University. In 2011 he cofounded ODYS S.r.l., a company specialized in developing model predictive control systems for industrial production.
He has published more than 350 papers in the areas of model predictive control, automotive control, hybrid systems, optimization (H-Index: see Google Scholar page) and is co-inventor of 13 patents. He is author or coauthor of various MATLAB toolboxes for model predictive control design, including the Model Predictive Control Toolbox (The Mathworks, Inc.) and the Hybrid Toolbox.
He was an Associate Editor of the IEEE Transactions on Automatic Control during 2001-2004 and Chair of the Technical Committee on Hybrid Systems of the IEEE Control Systems Society in 2002-2010 (read article). As a member of the Technical Activities Board of the IEEE Control Systems Society, he served on the Program Committee of the IEEE CDC 2002, 2004, 2008. He was Program Committee member of the "Hybrid Systems Computation and Control" workshops 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, of the "1st IFAC Workshop on Estimation and Control of Networked Systems (NecSys'09), of the IFAC Conference on the Analysis and Design of Hybrid Systems (ADHS) in 2006 and 2009, and of the Int. Conf. on Informatics in Control, Automation and Robotics, 2004, 2005 editions.
He received the IFAC High-Impact Paper Award for the 2011-14 triennial. He has been an IEEE Fellow since 2010. He received the best master thesis award "G. Barzilai", IEEE Centre and South Italy section, 4th edition, and best master thesis award "R. Mariani", AEI (Italian Electrotechnical Association) for year 1993.
Mr. Stelios PROCOPIOU
Chrysalis LEAP, Cyprus
From an idea to a business
The course will focus on providing the participants with the basic knowledge and skills needed to start exploring the potential of such an idea, by identifying their first potential market and customers. In this context, the course aims to:
• Refine and define their offering as specifically as possible.
• Identify and start exploring their first target market(s).
• Identify their first potential customers, assess their needs and how their offering addresses those needs (their value proposition).
• Have a first indication of the size of the business opportunity (a first look on simple financials).
• Define their next steps.
Stelios Procopiou is a Co-Founder and the Managing Director of Chrysalis LEAP, the first cleantech accelerator in Cyprus and Regional Partner of EIT Climate-KIC.
He is a First-Class Honours graduate of Imperial College, London, a Fellow Chartered Accountant, Member of the Institute of Chartered Accountants in England & Wales (ICAEW), a holder of the Chartered Wealth Manager Qualification and Chartered Fellow Member of the Chartered Institute for Securities and Investment (CISI) and a CFA Charter holder and Member of the CFA Institute.
He has extensive experience in the financial sector and is actively involved in initiatives promoting entrepreneurship and innovation.