Professor Plamen Angelov – Lancaster University, UK
Empirical Approach: How to get Fast, Interpretable Deep Learning
Plamen Angelov, Lancaster University, UK
We are witnessing an explosion of data (streams) being generated and growing exponentially. Nowadays we carry in our pockets Gigabytes of data in the form of USB flash memory sticks, smartphones, smartwatches etc. Extracting useful information and knowledge from these big data streams is of immense importance for the society, economy and science. Deep Learning quickly become a synonymous of a powerful method to enable items and processes with elements of AI in the sense that it makes possible human like performance in recognising images and speech. However, the currently used methods for deep learning which are based on neural networks (recurrent, belief, etc.) is opaque (not transparent), requires huge amount of training data and computing power (hours of training using GPUs), is offline and its online versions based on reinforcement learning has no proven convergence, does not guarantee same result for the same input (lacks repeatability).
The speaker recently introduced a new concept of empirical approach to machine learning and fuzzy sets and systems, had proven convergence for a class of such models and used the link between neural networks and fuzzy systems (neuro-fuzzy systems are known to have a duality from the radial basis functions (RBF) networks and fuzzy rule based models and having the key property of universal approximation proven for both).
In this talk he will present in a systematic way the basics of the newly introduced Empirical Approach to Machine Learning, Fuzzy Sets and Systems and its applications to problems like: anomaly detection, clustering, classification, prediction and control. The major advantages of this new paradigm is the liberation from the restrictive and often unrealistic assumptions and requirements concerning the nature of the data (random, deterministic, fuzzy), the need to formulate and assume a priori the type of distribution models, membership functions, the independence of the individual data observations, their large (theoretically infinite) number, etc. From a pragmatic point of view, this direct approach from data (streams) to complex, layered model representation is automated fully and leads to very efficient model structures. In addition,
the proposed new concept learns in a way similar to the way people learn – it can start from a single example. The reason why the proposed new approach makes this possible is because it is prototype based and non-parametric.
 P. Angelov, Autonomous Learning Systems: From Data Streams to Knowledge in Real time, John Willey and Sons, Dec.2012, ISBN: 978-1-1199-5152-0.
 P. Angelov, X. Gu, D. Kangin, Empirical data analytics, International Journal of Intelligent Systems, 32(12), 1261–1284, 2017.
 P. Angelov, X. Gu, J. Principe, A generalized methodology for data analysis, IEEE Transactions on Cybernetics, DOI: 10.1109/TCYB.2017.2753880, 2017.
 P. Angelov, X. Gu, J. Principe, Autonomous learning multi-model systems from data streams, IEEE Transactions on Fuzzy Systems, DOI:10.1109/TFUZZ.2017.2769039, 2017.
 P. Angelov, X. Gu, MICE: Multi-layer multi-model images classifier ensemble, in IEEE International Conference on Cybernetics (CYBCONF), Exeter, UK, 2017, pp. 1-8.
 P. Angelov, X. Gu, A Cascade of deep learning fuzzy rule-based image classifier and SVM, in IEEE International Conference on Systems, Man, and Cybernetics (SMC2017), Banff, Canada, 2017
 X. Gu, P. Angelov, C. Zhang, P. Atkinson, A massively parallel deep rule-based ensemble classifier for remote sensing scenes, IEEE Geoscience and Remote Sensing Letters, vol. 15 (3), pp. 345-349, 2018.
 X. Gu, P. Angelov, Semi-supervised deep rule-based approach for image classification, Applied Soft Computing, vol. 68, pp. 53-68, July 2018.
Biographical data of the speaker
Prof. Plamen P. Angelov (MEng 1989, PhD 1993, DSc 2015) is a Fellow of the IEEE, of the IET and of the HEA. He is Vice President of the International Neural Networks Society (INNS) and IEEE Distinguished Lecturer (2017-2019). He has 25+ years of professional experience in high level research and holds a Personal Chair in Intelligent Systems at Lancaster University, UK. He formed and led two research groups (Intelligent Systems, 2010-2013 and Data Science, 2014-2017) at the School of Computing and Communications with over 20 academics, researchers and PhD students each and now is the Director of LIRA (Lancaster Intelligent, Robotic and Autonomous systems) Research Centre with over 30 academics. He has authored or co-authored over 300 peer-reviewed publications in leading journals, peer-reviewed conference proceedings, 6 patents, two research monographs (by Wiley, 2012 and Springer, 2002) cited over 7000 times with an h-index of 39 and i10-index of 117. His single most cited paper has 840 citations. 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 (including several multimillion ones) 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 Cybernetics. He gave over 20 key note talks at high profile conferences. Prof. Angelov was General co-Chair of a number of high profile conferences and a series of annual IEEE Symposia on Evolving and Adaptive Intelligent Systems and more recently on Deep Learning. Dr Angelov is the founding Chair of the Technical Committee on Evolving Intelligent Systems, SMC Society of the IEEE and was previously chairing the Standards Committee of the Computational Intelligent Society of the IEEE (2010-2012). He was also a member of International Program Committee of over 100 international conferences (primarily IEEE). More details can be found at www.lancs.ac.uk/staff/angelov
Professor Chrisina Jayne – Oxford Brookes University, UK
Explainable Artificial Neural Network Models
Artificial Neural Networks (ANNs) have become the state of the art technology for object recognition, speech recognition, natural language processing, and many other applications. The availability of large datasets, computational power and rapid improvements in training algorithms have enabled the successful training of ANN models with many layers and millions of parameters. Systems based on such deep ANN models have very impressive performance on a variety of complex tasks. However, these models are highly non-linear and can be seen as black boxes, i.e. there is no explanation of how a prediction or a decision is made by such system. This is a major problem for applications where an explanation or interpretation is needed in order to develop robust autonomous intelligent systems, automatic medical diagnosis, or financial predictions. In this talk I will review the recent research advances in relation to explainable deep neural network models, practical algorithms and tools that can help practitioners and users to better understand the strength and weakness of a model, as well as how to improve a given model.
Received the Ph.D. degree in applied mathematics from Sofia University, Sofia, Bulgaria in 1998. She is currently the Head of the School of Engineering, Computing and Mathematics at Oxford Brookes University, UK. Her research relates to developing and applying novel methods for modal learning in artificial neural networks and deep neural networks. She authored over 70 peer-reviewed publications. Chrisina is a coordinator of the International Neural Network Society's Special Interest Group on Engineering Applications of Neural Networks. She chaired the Engineering Applications of Neural Network Conference (EANN) in 2012 and 2014 and served as the Program Chair of the International Joint Conference on Neural Networks (IJCNN) in 2017.
Professor Anthony Pipe, Bristol Robotics Laboratory, UK
Safe and Useful Human-Robot Interaction: from Connected Autonomous Vehicles to Care Robotics
An underlying theme of a great deal of recent robotics and autonomous systems research involves taking robot technology out of the isolated environments typified by manufacturing shop floors, so that they can work with and amongst us to improve our lives. In this context, Prof. Pipe will review the work of the Bristol Robotics Laboratory in th
Prof. Anthony Pipe is Deputy Director of Bristol Robotics Laboratory (BRL). He has over 200 international refereed publications and a BRL income of over £10M in R&D grants since 2013. He has 35 years of experience in advanced technology systems integration, gained from working in industry, academia or collaborations of both. His main foci are in ensuring robustness, safety and usefulness of robot devices engaged in safety-critical close-proximity Human-Robot Interaction. He was BRL PI on the EPSRC ‘Trustworthy Robotic Assistants’ project, is currently BRL PI on the EPSRC Programme Grant ‘Robotics for Nuclear Environments’ and the EPSRC Hub Grant ‘National Centre for Nuclear Robotics’. He has/is also involved with the EPSRC Bristol Centre for Doctoral Training in Robotics and Autonomous Systems (FARSCOPE), two EU projects (ECHORD++, TERRINET) on translation of research into industry, and a number of medical/Assisted Living projects, e.g. RAFS and I-DRESS. Prof. Pipe is also deeply involved in a number of UK funded Connected Autonomous Vehicle projects with a total value exceeding £27M: VENTURER (technology integration lead), FLOURISH (older adults as early adopters of CAV technology and CAV cyber-security), CAPRI and ROBOPILOT (new methods for Verification & Validation of safety for both).