Invited Speakers

George Cybenko

George Cybenko (Dartmouth College, USA)

Deep Learning of Behaviors [Slides]

Abstract:  Deep learning has generated much research and commercialization interest recently. In a way, it is the third incarnation of neural networks as pattern classifiers, using insightful algorithms and architectures that act as unsupervised auto-encoders which learn hierarchies of features in a dataset. After a short review of that work, we will discuss computational approaches for deep learning of behaviors as opposed to just static patterns. Our approach is based on structured non-negative matrix factorizations of matrices that encode observation frequencies of behaviors. These techniques can be used to robustly characterize and exploit diverse behaviors in security applications such as covert channel detection and coding.  Examples of such applications will be presented. 

Short biography: George Cybenko is the Dorothy and Walter Gramm Professor of Engineering at Dartmouth. Professor Cybenko has made research contributions in signal processing, neural computing, parallel computing and computational behavioral analysis. He was the Founding Editor-in-Chief of IEEE/AIP Computing in Science and Engineering and IEEE Security & Privacy. He recently started IEEE Transactions on Computational Social Systems as founding EIC. He has served on the Defense Science Board (2008-2009), US Air Force Scientific Advisory Board and on review and advisory panels for DARPA, IDA, BAE Systems and Lawrence Livermore National Laboratory. Professor Cybenko is a Fellow of the IEEE and received his BS (Toronto) and PhD (Princeton) degrees in Mathematics. He has held visiting appointments at MIT, Stanford and Leiden University where we has the Kloosterman Visiting Distinguished Professor. Cybenko is co-founder of Flowtraq Inc (www.flowtraq.com) which focuses on commercial software and services for large-scale network flow analytics.


Marcello Pelillo

Marcello Pelillo (Ca' Foscari University, Italy)

Similarity-based Pattern Recognition: A Game-theoretic Perspective [Slides]

Abstract: Similarity-based methods are emerging as a powerful tool in pattern recognition and machine learning because of their ability to overcome the intrinsic limitations of traditional feature-vector approaches. By departing from vector-space representations, however, one is confronted with the challenging problem of dealing with (dis)similarities that do not necessarily possess the Euclidean behavior or not even obey the requirements of a metric. In this talk, I will maintain that game theory offers an elegant and powerful conceptual framework which serves well this purpose, and I will describe recent attempts aimed at formulating various similarity-based pattern recognition problems from a game-theoretic perspective. Particular emphasis will be given to evolutionary-based models which, in contrast to the classical theory, offer an intriguing dynamical system perspective. Finally, I will descrive some applications of this approach within the context of multiple classifier systems.

Short biography: Marcello Pelillo is Full Professor of Computer Science at Ca' Foscari University in Venice, Italy, where he directs the European Center for Living Technology (ECLT) and the Computer Vision and Pattern Recognition group. He held visiting research positions at Yale University, McGill University, the University of Vienna, York University (UK), the University College London, and the National ICT Australia (NICTA). He has published more than 200 technical papers in refereed journals, handbooks, and conference proceedings in the areas of pattern recognition, computer vision and machine learning. He is General Chair for ICCV 2017 and has served as Program Chair for several conferences and workshops, many of which he initiated (e.g., EMMCVPR, SIMBAD, IWCV). He serves (has served) on the Editorial Boards of the journals IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Pattern Recognition, IET Computer Vision, Frontiers in Computer Image Analysis, Brain Informatics, and serves on the Advisory Board of the International Journal of Machine Learning and Cybernetics. Prof. Pelillo is a Fellow of the IEEE and a Fellow of the IAPR.