Keynote Lectures

Evolving Art
Penousal Machado, University of Coimbra, Portugal

Computational Sustainability
Carla Gomes, Cornell University, United States

Understanding Future Technologies through Agent-Based Simulation
Michal Pechoucek, Czech Technical University in Prague, Czech Republic

Continuous Learning in Large-scale Problems: The Case of Multi-script Historical Handwritten Document Collections
Lambert Schomaker, University of Groningen, Netherlands

Evolving Art

Penousal Machado
University of Coimbra
Portugal

Brief Bio
Penousal Machado leads the Cognitive and Media Systems at the University of Coimbra. His research interests include Evolutionary Computation, Computational Creativity, and Evolutionary Machine Learning. In addition to the numerous scientific papers in these areas, he is the recipient of scientific awards, including the EvoStar Award for Outstanding Contribution to Evolutionary Computation in Europe and the award for Excellence and Merit in Artificial Intelligence granted by the Portuguese Association for Artificial Intelligence. His works have been presented in venues such as the National Museum of Contemporary Art (Portugal) and the “Talk to me” exhibition of the Museum of Modern Art, NY (MoMA).

Abstract
Evolutionary Computation techniques have been applied to several fields in the Arts in recent years. This talk overviews how they have been used to create different types of artifacts, and how past developments relate to current approaches, trends and challenges. The focus is to address a main challenge in the field, fitness assignment, analyzing this from the perspective of the interplay between the evolutionary system and the user, and discussing how Machine Learning, Evolutionary Computation and HCI techniques can be combined to create Computer Aided Creativity systems that allow the users to express their artistic or aesthetic intentions.

Computational Sustainability

Carla Gomes
Cornell University
United States

Brief Bio
Carla Gomes is a Professor of Computer Science and the director of the Institute for Computational Sustainability at Cornell University. Gomes received a Ph.D. in computer science in the area of artificial intelligence and operations research from the University of Edinburgh. Her research area is Artificial Intelligence with a focus on large-scale constraint reasoning, optimization, and machine learning. Recently, Gomes has become deeply immersed in research in the new field of Computational Sustainability. From 2007-2013 Gomes led an NSF Expeditions-in-Computing in Computational Sustainability that nucleated the new field of Computational Sustainability. Gomes is currently the lead PI of a new NSF Expeditions-in-Computing that established CompSustNet, a large-scale national and international research network, to further expand the field and Computational Sustainability. Gomes is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Fellow of the Association for Computing Machinery (ACM), and a Fellow of American Association for the Advancement of Science (AAAS).

Abstract
Computational sustainability is a new interdisciplinary research field with the overarching goal of developing computational models, methods, and tools to help manage the balance between environmental, economic, and societal needs for a sustainable future. I will provide an overview of computational sustainability, with examples ranging from wildlife conservation and biodiversity, to poverty mitigation and materials discovery for renewable energy materials. I will highlight cross-cutting computational themes, opportunities, and challenges in Artificial Intelligence to address sustainability problems.

Understanding Future Technologies through Agent-Based Simulation

Michal Pechoucek
Czech Technical University in Prague
Czech Republic

Brief Bio
Prof. Ing. Michal Pechoucek, M.Sc, Dr. is a full professor in computer science at the Czech Technical University (CTU). He is the Founder and Head of the Artificial Intelligence Center and the Chair of Department of Computer Science at CTU. He is also a Director of the Research Center for Informatics, Center of Excellence, and a Founding Director of the Open Informatics, a research oriented computer science study programme at CTU-FEL. Michal Pechoucek has been a Principal Investigator (PI) on more than 30 research contracts and grants provided by US Air Force, US Army CERDEC and Office for Naval Research. He has been a PI on two projects funded by the Czech Science Foundation (GACR). He has been running several research contracts funded by the FAA and has collaborated on two additional research grants funded by NASA. His research has been also funded by industry including Google, FOXCON, Procter&Gamble, Rockwell Automation, FOXCON, Denso AUTOMOTIVE, CADANCE Design Systems, SAAB and others. Michal Pechoucek is the author of more than 200 papers, including 47 WoS impact-factor journal publications, his H-index is 29/13/13 (Google Scholar/WoS/Scopus) and number of citations is 3397/427/744 (Google Scholar/WoS/Scopus). In 2015 he has been put on the New Europe 100, the list of outstanding challengers who are leading world-class innovation from Central and Eastern Europe. He has been jointly with his colleagues a recipient of many awards for technical excellence and best paper awards. He served as the chairman of the board of directors of European Association for Multiagent Systems (EUMAS) and is a member of the board of directors of International Foundation of Autonomous Agents and Multiagent Systems (IFAAMAS). He is a honorary member of Artificial Intelligence Application Institute at University of Edinburgh. He is the co-founder of Cognitive Security (acquired by CISCO Systems in 2013). As a result of the acquisition, Michal Pechoucek have build and directed CISCO Systems R&D Center (until 2016), specialised in machine learning analytics for cyber security. Besides, he also co-founded AgentFly Technologies and BlindSpot Solutions.

Abstract
Current world is driven by data and superb analytical capability provided by state-of-the-art machine learning research. We assume that there exist classes of important prediction problems related to interaction among autonomous rational entities, for which statistical data analysis is not sufficient enough (such as understanding of future operation of drones in urban environment or massive deployment of autonomous vehicles in existing car traffic). We propose to complement modern data analysis with state-of-the-art procedural and decentralised computational modelling methods referred to as agent-based simulation. We argue that agent-based simulation can help us to understand and to solve the problems of near future for which there are no empirical data yet available. During the keynote talk we will discuss concepts, results as much as deployment visions and open problems and challenges of agent-based simulation.

Continuous Learning in Large-scale Problems: The Case of Multi-script Historical Handwritten Document Collections

Lambert Schomaker
University of Groningen
Netherlands
http://www.ai.rug.nl/~lambert/

Brief Bio
Lambert Schomaker (19-2-1957) is professor in artificial intelligence at the university of Groningen since 2001 and director of the AI institute at this university. He is known for research in simulation and recognition of handwriting, writer identification, style-based document dating and other studies in pattern recognition and machine learning. He has (co)authored over 200 publications and was involved in the organization of many conferences in handwriting recognition and document analysis. In recent years he and his team have worked on the Monk system: an interactively trainable search engine and e-Science service for historical manuscripts. The availability of up to thousands of training images for single classes of complex patterns has brought pattern recognition and machine learning into the ballpark of big data. Other recent work is in the area of robotics and industrial maintenance, in the EU ECSEL project Mantis. In 2015, he became co-chair of the Data Science and Systems Complexity center at the Faculty of Science and Engineering at the University of Groningen. In 2017, he joined the CogniGron center for cognitive systems and materials in a large-scale seven-year project in neuromorphic computing. He is a member of the IAPR and senior member of IEEE.

Abstract
Recent advances in deep learning by means of convolutional neural networks are very impressive in many application domains. Are these methods also suitable for the recognition of -hitherto unseen- handwritten documents in a rare script and language? What to do if the amount of training data is severely limited? What to do if user requirements are continuously changing over time, requiring not only text recognition but also the characterization of documents in terms of writer identity, general style or 'estimated date of production'? The presentation will focus on the discrepancies between current research habits and the requirements of large-scale machine learning in big data in the highly time-variant context of the Monk project. Many low-level technical adaptations are needed to elevate toy-level machine learning tools to a high-performance computing context. More interestingly, new concepts are needed from AI, to allow for an increasingly autonomous mode of learning, as opposed to the current non-scalable paradigm which is characterized by 'one data set / one PhD student / good results'. Results indicate that modern deep learning and regular pattern recognition need to live side by side in a large-scale real-world system in order to realize usable results, in a process of mutual collaboration between end users and computing resources.