Plamen Angelov

Organization: School of Computing and Communications, Lancaster University, UK
Homepage: http://www.lancs.ac.uk/staff/angelov

Prof. Angelov is Vice President of the International Neural Networks Society (INNS) for Conference and Governor of the Systems, Man and Cybernetics Society of the IEEE. He has 30 years of professional experience in high level research and holds a Personal Chair in Intelligent Systems at Lancaster University, UK. He founded in 2010 the Intelligent Systems Research group which he led till 2014 when he founded the Data Science group at the School of Computing and Communications before going on sabbatical in 2017 and established LIRA (Lancaster Intelligent, Robotic and Autonomous systems) Research Centre (www.lancaster.ac.uk/lira) which includes over 30 academics across different Faculties and Departments of the University. He is a founding member of the Data Science Institute and of the CyberSecurity Academic Centre of Excellence at Lancaster. He has authored or co-authored 300 peer-reviewed publications in leading journals, peer-reviewed conference proceedings, 3 granted patents and 3 research monographs cited 9000+ times with an h-index of 49 and i10-index of 160. He has an active research portfolio in the area of computational intelligence and machine learning and internationally recognised results into online and evolving learning and algorithms for knowledge extraction in the form of human-intelligible fuzzy rule-based systems. Prof. Angelov leads numerous projects funded by UK research councils, EU, industry, UK MoD. His research was recognised by "The Engineer Innovation and Technology 2008 Special Award" and "For outstanding Services" (2013) by IEEE and INNS. He is also the founding co-Editor-in-Chief of Springer's journal on Evolving Systems and Associate Editor of several leading international scientific journals, including IEEE Transactions on Fuzzy Systems, IEEE Transactions on Systems, Man and Cybernetics as well as of several other journals such as Applied Soft Computing, Fuzzy Sets and Systems, Soft Computing, etc.

Keynote talk - Explainable-by-Design Highly Efficient Deep Learning

Current ML approaches are focused primarily on accuracy and overlook explainability, the semantic meaning of the internal model representation, reasoning and its link with the problem domain. They also overlook the efforts to collect and label training data and rely on assumptions about the data distribution that are often not satisfied. The most efficient algorithms that have fuelled interest towards ML and AI recently are also computationally very hungry – they require specific hardware accelerators such as GPU, huge amounts of labelled data and time. They produce parameterized models with hundreds of millions of coefficients, which are also impossible to interpret or be manipulated by a human. Once trained, such models are inflexible to new knowledge. They cannot dynamically evolve their internal structure to start recognizing new classes. They are good only for what they were originally trained for. They also lack robustness, formal guarantees about their behaviour and explanatory and normative transparency. This makes problematic use of such algorithms in high stake complex problems such as aviation, health, bailing from jail, etc. where the clear rationale for a particular decision is very important and the errors are very costly.

All these challenges and identified gaps require a dramatic paradigm shift and a radical new approach. In this talk the speaker will present such a new approach towards the next generation of computationally lean ML and AI algorithms that can learn in real-time using normal CPUs on computers, laptops, smartphones or even be implemented on chip that will change dramatically the way these new technologies are being applied. It is explainable-by-design. It focuses on addressing the open research challenge of developing highly efficient, accurate ML algorithms and AI models that are transparent, interpretable, explainable and fair by design. Such systems are able to self-learn lifelong, and continuously improve without the need for complete re-training, can start learning from few training data samples, explore the data space, detect and learn from unseen data patterns, collaborate with humans or other such algorithms seamlessly.

Peter Kormushev

Organization: Robot Intelligence Lab, Imperial College London, UK http://www.imperial.ac.uk/robot-intelligence
Phone: +44 (0)20 7594 9235
Homepage: https://www.imperial.ac.uk/people/p.kormushev,

Dr Petar Kormushev is a Lecturer (Assistant Professor) in Robotics at the Dyson School of Design Engineering, Imperial College London (UK). He is also the founder and director of the Robot Intelligence Lab and an Academic Fellow of the Data Science Institute at Imperial College London. He holds a PhD in Computational Intelligence from Tokyo Institute of Technology, an MSc in Artificial Intelligence, and an MSc in Bio- and Medical Informatics. Previously, Dr. Kormushev was a visiting Senior Research Fellow at King’s College London, and a Research Team Leader at the Advanced Robotics department of the Italian Institute of Technology (IIT). Dr Kormushev's research focus is on the application of machine learning algorithms to robotics, especially reinforcement learning for intelligent robot behaviour. He is an expert in bipedal robot locomotion, with 8+ years of research experience on bipedal walking robots such as WALK-MAN, COMAN, WABIAN-2R, cCub, iCub, HOAP-2, and SLIDER. He has made significant contributions to agile online gait generation and balance control for humanoid robots in successful H2020 and FP7 EU projects. Dr. Kormushev is also an expert in robot skill learning, with 12+ years of research experience in machine learning for robotics, including reinforcement learning and deep learning for robot manipulation and control. His long-term research goal is to create autonomous robots that can learn by themselves, adapt to dynamic environments, and collaborate safely with people.

Keynote talk - Towards Practical Robot Intelligence for Manipulation and Locomotion

The future of robotics looks very promising. We expect robots to do the dirty, dull and dangerous jobs for us. We rely on robots to assist in healthcare. We hope that collaborative robots will make our jobs easier at work, and welcome them in our homes as toys or "smart" assistants. However, there are still many practical obstacles preventing robots from more widespread use. For example, ability to adapt to unstructured environments, ability to learn quickly new skills, ability to transfer prior knowledge to new tasks, etc. In this talk, I will give many examples of challenging tasks for robots in manipulation and locomotion, and describe my efforts towards solving them from a very applied, practical aspect. I will also describe briefly my personal research journey in robotics and machine learning, with many photos and videos of robot experiments I have done over the last 10+ years, and explain which approaches have worked well, and which have failed the test of time. I will finish with a discussion about the future of robotics, and what are the immediate next challenges we need to overcome to achieve our "robotic dreams".

Julian. F. Miller

Organization: Department of Electronic Engineering, University of York, UK
Homepage: https://www.cartesiangp.com/julian-miller

Dr. Miller obtained BSc in Physics from the University of London, PhD in Nonlinear Mathematics from the City University and Postgraduate Certificate in Learning and Teaching in Higher Education from University of Birmingham. He is currently an Honorary Fellow (formerly Reader) in the Department of Electronic Engineering at the University of York. He has chaired or co-chaired seventeen international workshops, conferences and conference tracks in Genetic Programming (GP), Evolvable Hardware. He is a former associate editor of IEEE Transactions on Evolutionary Computation and an associate editor of the Journal of Genetic Programming and Evolvable Machines and Natural Computing. He is on the editorial board of the journals: Evolutionary Computation, International Journal of Unconventional Computing and Journal of Natural Computing Research. He has publications in genetic programming, evolutionary computation, quantum computing, artificial life, evolvable hardware, computational development, and nonlinear mathematics. Dr. Miller is a highly cited author with over 10,000 citations and over 230 refereed publications in related areas. He has authored or co-authored 44 journal publications. He has given fourteen tutorials on genetic programming and evolvable hardware at leading conferences in evolutionary computation. He received the prestigious EvoStar award in 2011 for outstanding contribution to the field of evolutionary computation. He is the inventor of a highly cited method of genetic programming known as Cartesian Genetic Programming and edited the first book on the subject in 2011. He is also well known for proposing “evolution-in-materio” which asserts that computational functions could be evolved directly in materials by evolving configurations of applied physical variables without requiring a detailed understanding of the materials.

Keynote talk - Cartesian Genetic Programming

Cartesian Genetic Programming (CGP) is a very general technique that can be applied to a wide range of computational problems in many fields. It is a form of Genetic Programming (GP) which finds solutions to computational problems by evolving programs and other structures. CGP uses a very simple integer address-based representation of a program in the form of a directed graph. In various studies, CGP has been shown to be comparatively efficient to other GP techniques. The classical form of CGP has undergone a number of developments which have made it more useful, efficient and flexible in various ways. These include self-modifying CGP (SMCGP), cyclic connections (recurrent-CGP), encoding artificial neural networks (CGPANN) and automatically defined functions (modular CGP). SMCGP uses functions that cause the evolved programs to change themselves as a function of time. Recurrent-CGP allows evolution to create programs which contain cyclic, as well as acyclic, connections. CGP encoded artificial neural networks represent a powerful training method for neural networks.

CGP has been applied successfully to a variety of real-world problems, such as digital circuit design, visual object recognition and classification. More, recently it has been used to create a general AI approach inspired by biological development in which evolved neural programs create ANNs that simultaneously solve multiple problems. CGP has a dedicated web site at www.cartesiangp.com