Special Session Chairs

Ariel Ruiz-Garcia

Arm, UK

Email: ariel.9arcia@gmail.com

 

Dr Ariel Ruiz-Garcia received his PhD in Computing (Machine Learning) from Coventry University, UK. He is currently a Senior Artificial Intelligence Engineer at Arm Ltd., where he works on applied machine learning. His research is focused on the development of novel deep learning techniques for invariant feature learning with application to a wide range of domains and has resulted in several papers published in top tier international journals and conference proceedings. Dr Ruiz-Garcia is currently serving as a lead guest editor for the special issue on “Deep Representation and Adversarial Learning” in the Neural Networks journal. He is also serving a guest editor in the IEEE Transactions on Neural Networks and Learning Systems journal. He served as the lead organizer and chair of the special session on “Deep and Generative Adversarial Learning” at IJCNN 2019, and was a co-organizer and chair of a special session on Intelligent Physiological and Affect Aware Systems at IEEE WCCI 2018. He has delivered invited talks on Generative Adversarial Learning at reputed venues such as the 5th Big Data in Cyber Security Conference. He has been awarded several travel grants to attend highly ranked conferences such as the International Conference on Machine Learning (ICML17) and International Conference on Artificial Neural Networks (ICANN16-18), he has received best poster awards, and has received many research grants. Dr Ruiz-Garcia is a member of IEEE and the IEEE Computational Intelligence Society and is an active PC member and chair for several top tier journals and conferences including ICML, IJCNN, ICANN, IEEE TETCI, IEEE TAC, IEEE TNNLS, etc.

 

 

Vasile Palade

Coventry University, UK

Email: vasile.palade@coventry.ac.uk

 

Vasile Palade is currently Professor of Artificial Intelligence and Data Science at Coventry University, UK. He joined Coventry University as a Reader in Pervasive Computing, in September 2013, after working for many years as a Lecturer with the Department of Computer Science of the University of Oxford, UK. His expertise spans across several machine learning domains and encompasses neural networks and deep learning, neuro-fuzzy systems, various nature inspired algorithms such as swarm optimization algorithms, hybrid intelligent systems, class imbalance learning.  Application areas include image processing, web usage mining and social network data analysis, industrial fault diagnosis, among others. He published many papers in machine learning and applications in prestigious venues (i.e., 170+ papers and several books; 4780 citations and h-index 31, according to Google.Scholar) and has delivered keynote talks to reputed international conferences on machine learning and applications. He plays an active role in the computational intelligence community worldwide. Dr. Palade is an IEEE Senior Member. He is a member of the Technical Committee on Machine Learning of the IEEE SMC Society and he is the Chair of the IFIP Working Group on Computational Intelligence TC12.9. He is acting as an Associate Editor for several reputed journals, such as Knowledge and Information Systems, Neurocomputing, International Journal on Artificial Intelligence Tools, among others. He is regularly involved in organizing reputed conferences; he was Co-Chair for the International Conference on Machine Learning and Applications, Washington D.C., 2010 (ICMLA 2010), Co-Chair for ICMLA 2015, Miami-USA, Dec 2015,  General Chair for KES2003, Oxford, 2003, etc. 

 

Jürgen Schmidhuber

Co-Founder & Chief Scientist, NNAISENSE

Scientific Director, Swiss AI Lab IDSIA

Professor of AI, USI & SUPSI, Switzerland

http://people.idsia.ch/~juergen/whatsnew.html

Email: juergen@idsia.ch

 

In 1990, Jürgen Schmidhuber introduced a concept that has become very popular and is at the heart of the present special session: unsupervised learning without a teacher through two adversarial Neural Networks (NNs) that duel in a minimax game, where one NN minimizes the objective function maximized by the other. The first NN generates data through its output actions, the second NN predicts the data. The second NN minimizes its error, thus becoming a better predictor. But it is a zero sum game: the first NN tries to find actions that maximize the error of the second NN. The system exhibits what Schmidhuber called “artificial curiosity.” The first NN is motivated to invent actions that yield data that the second NN still finds surprising, until the data becomes familiar and eventually boring. Schmidhuber also used a similar adversarial zero sum game for another unsupervised method called "predictability minimization," where two NNs fight each other to discover a disentangled code of the incoming data, remarkably similar to codes found in the brain of mammals. Deep Learning Neural Networks of Schmidhuber’s lab (such as Long Short-Term Memory LSTM) have transformed machine learning and AI, and became available to billions of users through the world's most valuable public companies, e.g., for greatly improved (CTC-based) speech recognition on over 2 billion Android phones, greatly improved machine translation through Google Translate (2016) and Facebook (30 billion LSTM-based translations per week as of 2017), Apple's Siri and Quicktype on almost 1 billion iPhones (since 2016), the answers of Amazon's Alexa, and numerous other applications. In 2011, his team was the first to win official computer vision contests through deep GPU-based CNNs, with superhuman performance. His research group also established the fields of metalearning, mathematically rigorous universal AI and recursive self-improvement in universal problem solvers that learn to learn (since 1987). He is recipient of numerous awards, and Chief Scientist of the company NNAISENSE, which aims at building the first practical general purpose AI. He is also advising various governments on AI strategies.

 

Danilo Mandic

Imperial College London, UK

Email: d.mandic@imperial.ac.uk

 

Biography: Danilo P. Mandic is a Professor in signal processing with Imperial College London, UK, and has been working in the areas of statistical signal processing and machine learning. He is a Fellow of the IEEE, member of the Board of Governors of International Neural Networks Society (INNS), member of the Big Data Chapter within INNS and member of the IEEE SPS Technical Committee on Signal Processing Theory and Methods. He has received five best paper awards in Brain Computer Interface, runs the Smart Environments Lab at Imperial College, and has about 500 publications in international journals and conferences. He has authored two research monographs on neural networks, Recurrent Neural Networks for Prediction (Wiley, 2001) and Complex Valued Nonlinear Adaptive Filters: Nonlinearity, Widely Linear and Neural Models (Wiley, 2009). He has also co-authored a two volume monograph Tensor Networks for Dimensionality Reduction and Large Scale Optimisation (Now Publishers, 2016, 2017). Prof Mandic has given a number of keynote speeches and tutorials at foremost international conferences (IJCNN, ICASSP), and has received the President Award for Excellence in Postgraduate Supervision at Imperial. In terms of the applications of his work, he is a pioneer of Hearables, a radically new in-the-ear-canal system for the recording of the Electroencephalogram (EEG) and vital signs. This work appeared in IEEE Spectrum, MIT Technology Review and has won several awards.

 

Clive Cheong Took

Royal Holloway (University of London), UK

Email: Clive.CheongTook@rhul.ac.uk

 

Dr Clive Cheong Took is a Senior Lecturer at Royal Holloway University of London within its Department of Electronic Engineering. He was previously a Lecturer in Computational Intelligence at the University of Surrey, and he received his PhD in Signal Processing from Cardiff University. He has published 26 high-quality journal papers, including 15 IEEE Transactions (2012). Since 2012, he has been working in the area of neural networks and deep learning, especially in the area of Brain Computer Interfacing. He is currently an affiliate Member for IEEE Signal Processing Theory and Methods Technical Committee, is on various IEEE conference committees such as ICASSP 2019, and has been on the editorial board of IEEE Transactions on Neural Networks and Learning Systems since 2014.