Pierre Baldi is a chancellor’s professor of computer science at University of California Irvine and the director of its Institute for Genomics and Bioinformatics.
Pierre Baldi received his Bachelor of Science and Master of Science degrees at the University of Paris, in France. He then obtained his Ph.D. degree in mathematics at the California Institute of Technology in 1986 supervised by R. M. Wilson.
From 1986 to 1988, he was a postdoctoral fellow at the University of California, San Diego. From 1988 to 1995, he held faculty and member of the technical staff positions at the California Institute of Technology and at the Jet Propulsion Laboratory, where he was given the Lew Allen Award for Research Excellence in 1993. He was CEO of a start up company called Net-ID from 1995 to 1999 and joined University of California, Irvine in 1999.
Baldi’s research interests include artificial intelligence, statistical machine learning, and data mining, and their applications to problems in the life sciences in genomics, proteomics, systems biology, computational neuroscience, and, recently, deep learning.
Baldi has over 250 publications in his field of research and four books including
- “Bioinformatics: the Machine Learning Approach” (MIT Press, 1998; 2nd Edition, 2001, ISBN 978-0262025065) a worldwide best-seller
- “Modeling the Internet and the Web. Probabilistic Methods and Algorithms“, by Pierre Baldi, Paolo Frasconi and Padhraic Smyth. Wiley editors, 2003.
- “The Shattered Self—The End of Natural Evolution“, by Pierre Baldi. MIT Press, 2001.
- “DNA Microarrays and Gene Regulation“, Pierre Baldi and G. Wesley Hatfield. Cambridge University Press, 2002.
- Extensive gene gain associated with adaptive evolution of poxviruses
Baldi is a fellow of the Association for the Advancement of Artificial Intelligence (AAAI), the AAAS, the IEEE,and the Association for Computing Machinery (ACM). He is also the recipient of the 2010 Eduardo R. Caianiello Prize for Scientific Contributions to the field of Neural Networks and a fellow of the International Society for Computational Biology (ISCB).
Deep learning algorithm solves Rubik’s Cube faster than any human.
AI solves Rubik’s Cube in one second
TopicsMachine Learning, Deep Learning, Artificial Intelligence. Keynote Speaker of the Workshop on “Biologically Plausible Learning”.
Yoshua Bengio Paris, France) is a Canadian computer scientist, most noted for his work on artificial neural networks and deep learning. He was a co-recipient of the 2018 ACM A.M. Turing Award for his work in deep learning.He is a professor at the Department of Computer Science and Operations Research at the Université de Montréal and scientific director of the Montreal Institute for Learning Algorithms (MILA).(born 1964 in
Yoshua Bengio is Full Professor of the Department of Computer Science and Operations Research,head of the Montreal Institute for Learning Algorithms (MILA), CIFAR Program co-director of the CIFAR program on Learning in Machines and Brains, Canada Research Chair in Statistical Learning Algorithms. His main research ambition is to understand principles of learning that yield intelligence. He supervises a large group of graduate students and post-docs. His research is widely cited (over 80000 citations found by Google Scholar in September 2017, with an H-index of 101).
Yoshua Bengio is currently action editor for the Journal of Machine Learning Research, associate editor for the Neural Computation journal, editor for Foundations and Trends in Machine Learning, and has been associate editor for the Machine Learning Journal and the IEEE Transactions on Neural Networks.
Yoshua Bengio was Program Chair for NIPS‘2008 and General Chair for NIPS‘2009 (NIPS is the flagship conference in the areas of learning algorithms and neural computation). Since 1999, he has been co-organizing the Learning Workshop with Yann Le Cun, with whom he has also created the International Conference on Representation Learning (ICLR). He has also organized or co-organized numerous other events, principally the deep learning workshops and symposiua at NIPS and ICML since 2007. Yoshua Bengio is Officer of the Order of Canada and member of the Royal Society of Canada.
Professor for Internet and Society at the Faculty of Electrical Engineering and Computer Science at Technische Universität Berlin, Director of the Weizenbaum Institute for the Networked Society, and guest professor in the Declarative Languages and Artificial Intelligence Group DTAI of the Department of Computer Science at KU Leuven.
The increasing use of machine learning and other AI techniques in real-world applications has been accompanied by an increasing realisation of problematic (side?)effects of these technologies. Computer scientists and interdisciplinary scholars have made progress in diagnosing and addressing issues such as data protection and fairness violations. Recently, techniques inspired by adversarial machine learning have received increasing attention. In this talk, I will present selected techniques and at the same time identify important (ethical?) dilemmas faced by scientists and practitioners who aim at “being more ethical” in data processing. In particular, I want to discuss problems of a persistent solutionism and methods that emphasize questions instead.
Professor Artur d’Avila Garcez, FBCS, is the Director of the Research Centre for Machine Learning at City, University of London, and the Director of The City Data Science Institute. He holds a Ph.D. in Computer Science (2000) from Imperial College London. He co-authored two books: Neural-Symbolic Cognitive Reasoning (Springer, 2009) and Neural-Symbolic Learning Systems (Springer, 2002), and has more than 150 peer-reviewed publications in the areas of Artificial Intelligence, Machine Learning, Neural Computing and Neural-Symbolic AI. Garcez is president of the Neural-Symbolic Learning and Reasoning Association (www.neural-symbolic.org), associate editor of the Journal of Logic and Computation and the IEEE Transactions on Neural Networks and Learning Systems, and editor of the Machine Learning Journal special track on learning and reasoning. He has served on the programme committees of all the major conferences in machine learning, artificial intelligence and neural computation, including IJCAI, NeurIPS, ECAI, ICML, AAAI, AAMAS and IJCNN. His research has received funding from the Nuffield foundation, the EU, the Daiwa Foundation, the Royal Society, Innovate UK, ESRC and EPSRC UK, CAPES-Brazil, and from industry, including IBM, Playtech plc and Kindred group.
Neural-symbolic computing seeks to benefit from the integration of symbolic AI and deep learning. In a neural-symbolic system, neural networks offer the machinery for efficient learning and computation, while symbolic knowledge representation and reasoning enables the use of prior knowledge, transfer learning and explainability. Neural-symbolic computing has found application in many areas including software systems’ specification, training and assessment in simulators, and the prediction of harm in online gambling for consumer protection. In this talk, I will introduce the principles of neural-symbolic computing and will exemplify its use in practice, with an emphasis on how it may enable trust in AI systems. I will conclude by discussing the main challenges, opportunities and current landscape of the research and development in neural-symbolic AI.
- Full professor of Computer Science, KU Leuven
- Director of Leuven.AI, the KU Leuven Institute for AI
- ERC AdG 2015
- EurAI Fellow, AAAI Fellow and IJCAI Trustee
- Guestprofessor at Örebro University at the Center for Applied Autonomous Sensor Systems
Prof. Dr. Luc De Raedt is currently Director of Leuven.AI, the KU Leuven Institute for AI, full professor of Computer Science at KU Leuven, and guestprofessor at Örebro University (Sweden) at the Center for Applied Autonomous Sensor Systems in the Wallenberg AI, Autonomous Systems and Software Program.
Luc De Raedt obtained his PhD in Computer Science from the KU Leuven (1991), was post-doctoral researcher of the Fund for Scientific Research, Flanders (FWO) (1991-99) and part-time assistant/associate professor (1993-1999) KU Leuven; full professor (C4) and Chair of the Machine Learning and Natural Language Processing Lab at the Albert-Ludwigs-University Freiburg, Germany (1999-2006); head of the Lab for Declarative Languages and Artificial intelligence at KU Leuven from (2015-2019).
Luc De Raedt’s research interests are in Artificial Intelligence, Machine Learning and Data Mining, as well as their applications. He is well known for his contributions in the areas of learning and reasoning, in particular, for his contributions to statistical relational learning, probabilistic and inductive programming. Today he is working on the next generation of programming languages, which can automatically learn from data, on combining probabilistic and logical reasoning and learning, on the automation of (data) science, and on verifying learning artificial intelligence systems and robotics. He is also now also focusing on integrating the probabilistic logics with neural networks and wants to apply these to reinforcement learning as well as program induction.
He has co-authored 320 works (according to DBLP), including 3 books, 10 papers in Artificial Intelligence (journal), 17 in Machine Learning (journal), and 36 at core AI conferences such as IJCAI, AAAI and ECAI. According to google scholar he is cited more than 16000 times and his h-index is 62. He is editor of 7 volumes with Lecture Notes in Computer Science. He has delivered numerous tutorials at major AI and machine learning conferences and events such as IJCAI (2015, 2016, 2017), AAAI (2018, 2016), ECAI (2014), MLSS (2015, 2019) and NIPS (2017); he has delivered keynote talks at numerous events such as ECAI (2020 planned), NeSy (2019), ECDA (2018), ECMLPKDD (2013), ICML (2008), IJCAI machine learning track (2015), ICLP (2015), KI (2017), AutoML (2018), IDA (2018), etc. In the last two years, he has delivered around 10 popular science talks on Artificial and Machine Learning in Flanders, both for industry and for the wide public (Bozar, FWO Kennismakers, Business for AI, &Leuven, etc.).
Luc De Raedt is proud of his students. He has (co)advised 27 Phd students and 17 post-docs. Many of his students have won prestigious awards, including an ERC Starting Grant (Jan Ramon), four ECCAI Dissertation awards for the best European thesis in AI (Kristian Kersting, Guy Van den Broeck, Niels Landwehr, Tias Guns), two IBM Belgium awards (Guy Van den Broeck and Niels Landwehr), the Dissertation Award of the Association for Constraint Programming (Tias Guns) and the Prize of the KU Leuven Research Council (Guy Van den Broeck). Guy Van den Broeck is also the 2019 of the IJCAI Computers and Thought Award, the premier award in the field of AI for researchers under the age of 35. Ten former mentees are now faculty members or independent research directors.
TopicsConstraint-Based Approaches to Machine Learning
Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy, while working partly as a visiting student at the School of Computer Science, McGill University – Montréal. 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, computer vision, and natural language processing. He was the leader of the WebCrow project supported by Google for automatic solving of crosswords, that outperformed human competitors in an official competition within the ECAI-06 conference. He has just published the book “Machine Learning: A Constrained-Based Approach,” where you can find his view on the field.
He has been an Associated Editor of a number of journals in his area of expertise, including The IEEE Transactions on Neural Networks and Neural Networks, and he has been 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 ECCAI (EurAI) (European Coordinating Committee for Artificial Intelligence), a fellow of the IEEE, and of IAPR. He is in the list of top Italian scientists kept by VIA-Academy.
TopicsRobustness and fairness for machine learning and Artificial Intelligence
Marta Kwiatkowska is a computer scientists who is developing modelling and analysis methods for complex systems, such as those arising in computer networks, electronic devices and biological organisms. The distinctive aspect of her work is its focus on probabilistic and quantitative verification techniques, as well as synthesis of correct-by-construction systems from quantitative specifications. Marta’s recent contributions have centred on safety and trust for robotics and Artificial Intelligence, and specifically safety and robustness guarantees for machine learning.
Marta led the development of the PRISM model checker (www.primmodelchecker.org), the leading tool in the area and widely used for research and teaching. PRISM has been applied to study, amongst others, wireless network protocols, security protocols, molecular signalling networks, DNA computation and cardiac pacemakers.
Marta has published over 300 papers during her career and received numerous keynote invitations. She won two ERC Advanced Grants, VERIWARE and FUN2MODEL, and is a co-investigator on the EPSRC Programme Grant on Mobile Autonomy. Marta was awarded an honorary doctorate from KTH Institute of Technology and is the first female winner of the Royal Society Milner Medal. She is a Fellow of the ACM, Member of Academia Europea and Fellow of the Royal Society.
Short Bio-Sketch for Professor Angelo Lucia
Professor Lucia is the Chester H Kirk Professor (1996-present) and Chair (2017-present) of the Department of Chemical Engineering at the University of Rhode Island (URI). Prior to joining URI, Dr. Lucia was a Full Professor at Clarkson University for 15 years. Professor Lucia’s research focus is in the general areas of modeling, simulation, optimization and analysis with applications in computational thermodynamics, process design, reservoir simulation, and metabolic networks. He has published over 100 journal articles and given over 200 presentations, and consulted for a wide range of industrial firms over his academic career. Prior to becoming an educator, Dr. Lucia worked for Union Carbide Corporation.
Viruses are not living entities; they consist of a collection of viron particles. Each particle is generally made of DNA or RNA encapsulated in capsid protein surrounded by a lipid layer. Viruses have two main goals:
1) invasion a host cell
Once inside the cell, a virus will take over the cell machinery, modifying or reprogramming cell metabolism for its own purposes. These modifications usually include increased rates of glycolysis, pentose phosphate (PEP) consumption, and glutaminolysis, which in turn result in increased citrate production and fatty acid production. Unfortunately, after a decade of research, understanding of viral metabolic reprogramming is still poorly understood. However, computer modeling, simulation and optimization offer unique opportunities to investigate mechanisms used by viruses to hijack cellular metabolism.
In this talk, an overview of the Nash Equilibrium approach to modeling metabolic networks and its application to viral metabolic reprogramming will be presented. A network of fifteen + pathways are used to model and simulate metabolic behavior of a cell infected with a virus. Specific attention will be given to studying increased amino acid, nucleotide, and fatty acid synthesis, changes in energy charge, and to identifying potential ways of ‘killing’ the virus.
TopicsMotor Control & Learning, Robotics, Machine Learning, Biomimetic Systems.
Jan Peters (born on August 14, 1976 in Hamburg, Germany) is a German computer scientist. He is Professor of Intelligent Autonomous Systems at Department of Computer Science of the Technische Universität Darmstadt and Head of the Robot Learning Group at the Max Planck Institute for Intelligent Systems.
Peters is renowned for his research in machine learning and robotics.
Jan Peters graduated from the University of Hagen in 2000 with a diplom in computer science and from Technical University of Munich in 2001 with a diplom in electrical engineering. Fron 2000 to 2001, he spent two semesters as visiting student at the National University of Singapore. He then studied at the University of Southern California where he earned a Master of Science degree in Computer Science and a Master of Science degree in Aerospace and Mechanical Engineering. He received his Ph.D. in Computer Science from the University of Southern California in 2007. Since 2011 he has been Head of the Intelligent Autonomous Systems Institute at the Technische Universität Darmstadt.
In 2008, Nicholas Roy, Russ Tedrake, Jun Morimoto and Jan Peters founded the IEEE Robotics and Automation Society’s Technical Committee on Robot Learning.
For his contributions, he has received the Robotics & Automation Early Career Award, the highest ranked early career award of the Institute of Electrical and Electronics Engineers, and the Young Investigator Award of the International Neural Network Society. In addition, he received an ERC Starting Grant in 2014 as well as numerous best paper awards. He was appointed Fellow of the Institute of Electrical and Electronics Engineers(IEEE) in 2019 “for contributions to robot learning of dexterous motor skills”.
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can learn tasks triggered by environmental context or higher level instruction. However, learning techniques have yet to live up to this promise as only few methods manage to scale to high-dimensional manipulator or humanoid robots. In this talk, we investigate a general framework suitable for learning motor skills in robotics which is based on the principles behind many analytical robotics approaches. It involves generating a representation of motor skills by parameterized motor primitive policies acting as building blocks of movement generation, and a learned task execution module that transforms these movements into motor commands. We discuss learning on three different levels of abstraction, i.e., learning for accurate control is needed to execute, learning of motor primitives is needed to acquire simple movements, and learning of the task-dependent „hyperparameters“ of these motor primitives allows learning complex tasks. We discuss task-appropriate learning approaches for imitation learning, model learning and reinforcement learning for robots with many degrees of freedom. Empirical evaluations on a several robot systems illustrate the effectiveness and applicability to learning control on an anthropomorphic robot arm. These robot motor skills range from toy examples (e.g., paddling a ball, ball-in-a-cup) to playing robot table tennis against a human being and manipulation of various objects.
Raniero Romagnoli is currently CTO of Almawave, that he joined in 2011, with the responsibility of defining and implementing the company’s technology strategy, with a special focus on R&D labs, helping Almawave create and evolve its products and solutions, that are based on proprietary Natural Language Processing technology to leverage speech and text information and communications in order to govern processes and improve both self and assisted engagement with users. Before joining Almawave Raniero worked for 2 years in RSA and before that Raniero worked for Hewlett Packard, for almost 10 years, in different technology and divisions, covering roles both in Product Management and R&D in intelligent support systems area. Raniero has a broad experience in the artificial intelligence field, starting from his research activities in the late ’90s on Machine Learning and Neural Networks for image processing, than in the security space, and since he joined Almawave in the field of speech and text analysis.
Many enterprises and corporations have several different repositories for both internal and external access where unstructured content is often key to manage. In this environments content analysis plays an important role in process automation and decision support systems, freeing the value of unstructured information However those companies need to pay careful attention to resource usage and return on investments, and to leveraging past investments and legacy systems. In such an ecosystem approaching the analysis of text using a combination of different natural language processing approaches, is key to obtaining a good balance between agility, task performance and resource usage in order to obtain the expected level of automation and the desired outcomes. Moreover transfer learning techniques a joint usage of various approaches, from traditional semantic analysis to knowledge graphs and reasoning, to the most recent use of Transformers, is often required also due to the particular data availability and distribution within the companies, that is also usually sparse, and domain dependent.
TopicsQuantum Machine Learning, Machine Learning
Maria Schuld works as a researcher for the Toronto-based
quantum computing start-up Xanadu, as well as for the Big Data and Informatics Flagship of the University of KwaZulu-Natal in Durban, South Africa. She received her PhD from the University of KwaZulu-Natal in 2017 for her work on the intersection of quantum computing and machine learning, which was published as the book “Supervised Learning with Quantum Computers” (Springer, 2018, co-authored by F. Petruccione). Besides her physics background Maria has a postgraduate degree in political science, and a keen interest in
the interplay of emerging technologies and society.
A popular approach to machine learning with quantum computers is to interpret the quantum device as a machine learning model that loads input data and produces predictions. By optimizing the quantum circuit, the “quantum model” can be trained like a neural network. This talk highlights different aspects of such “variational quantum machine learning algorithms”, including their role in the development of near-term quantum technologies, their close links to kernel methods, and how to get gradients of quantum computations. As a practical illustration, the integration of quantum circuits with machine learning libraries such as PyTorch and Tensorflow is demnostrated with the open-source software framework “PennyLane”.
TopicsMathematical Foundations of Machine Learning, Data Analysis, Semi-Supervised Learning, Active Learning
Ruth Urner is an assistant professor at York University in Toronto, Canada. She is also a faculty affiliate at Toronto’s Vector Institute. Previous to that she was a senior research scientist at the Max Planck Institute for intelligent systems in Tübingen, Germany, and a postdoctoral fellow at Carnegie Mellon’s Machine Learning department as well as at Georgia Tech. She received her PhD from the University of Waterloo for a thesis on statistical learning theory in 2013. She regularly serves as a senior program committee member of the major machine learning conferences, such as NeurIPS, ICML, AISTATS and COLT. Her research develops mathematical tools and frameworks for analyzing the possibilities and limitations of automated learning, with a focus on semi-supervised, active and transfer learning. Currently she is particularly interested in developing formal foundations for topics relating to societal impacts of machine learning, such as human interpretability and fairness in machine learning.
Isabel Valera is a full Professor at the Department of Computer Science of Saarland University, Saarbrücken (Germany) and an independent group leader at the MPI for Intelligent Systems in Tübingen (Germany). Prior to this, she has held a German Humboldt Post-Doctoral Fellowship, and a “Minerva fast track” fellowship from the Max Planck Society. She obtained my PhD in 2014 and MSc degree in 2012 from the University Carlos III in Madrid (Spain), and worked as postdoctoral researcher at the MPI for Software Systems (Germany) and at the University of Cambridge (UK). Isabel’s research focuses on developing machine learning methods that are flexible, robust, interpretable and fair.
Past Keynote Speakers
The Keynote Speakers of the previous editions:
- Jörg Bornschein, DeepMind, London, UK
- Michael Bronstein, Imperial College London, UK
- Nello Cristianini, University of Bristol, UK
- Peter Flach, University of Bristol, UK, and EiC of the Machine Learning Journal
- Marco Gori, University of Siena, Italy
- Arthur Gretton, UCL, UK
- Arthur Guez, Google DeepMind, Montreal, UK
- Yi-Ke Guo, Imperial College London, UK
- George Karypis, University of Minnesota, USA
- Vipin Kumar, University of Minnesota, USA
- George Michailidis, University of Florida, USA
- Kaisa Miettinen, University of Jyväskylä, Finland
- Stephen Muggleton, Imperial College London, UK
- Panos Pardalos, University of Florida, USA
- Jan Peters, Computer Science Department, Technische Universitaet Darmstadt, and Max-Planck Institute for Intelligent Systems, Germany
- Tomaso Poggio, MIT, USA
- Andrey Raygorodsky, Moscow Institute of Physics and Technology, Russia
- Mauricio G. C. Resende, Amazon.com Research and University of Washington Seattle, Washington, USA
- Ruslan Salakhutdinov, Carnegie Mellon University, USA, and AI Research at Apple
- My Thai, University of Florida, USA
- Richard E. Turner, Department of Engineering, University of Cambridge, UK