Abstract: 

     Big data (such as multimedia data (speech, video, and medical/biological data) analysis requires novel technologies to
efficiently process and analyze large quantities of data within tolerable elapsed times. Such a new emerging technology for
multidimensional big data is a multiway analysis via tensor networks and tensor decompositions. Modern applications such as
computational neuroscience, bioinformatics and pattern/image recognition generate massive amounts of data with multiple aspects
and high dimensionality. Tensors (i.e., multi-way arrays) and tensor networks could provide a natural representation for such
massive multidimensional data.  Dynamic tensor analysis allows us to discover meaningful hidden structures of complex data and
perform generalizations by capturing multi-linear and multi-aspect relationships. The challenge is how to analyze intractably
large-scale optimization problems, dimensionality reduction, feature extraction, classification and anomaly detection. In this
talk I will focus mostly on emerging tensor network models and associated algorithms for tensor train decompositions in potential
applications to wide class of very large-scale optimization problems.

About the speaker:
    Biodata: Prof. Andrzej CICHOCKI received the MSc (with honors), PhD and Dr Sc (Habilitation) degrees, all in electrical
engineering, from Warsaw University of Technology (Poland). Since 1976, he has been at the Warsaw University of Technology,
where he became a full Professor in 1995. He spent several years at University Erlangen-Nuerenberg (Germany) as an Alexander
-von-Humboldt Research Fellow and Guest Professor. He is currently a Senior Team Leader and Head of the laboratory for Advanced
Brain Signal Processing, at RIKEN Brain Science Institute (Japan). He is (co)author of more than 300 technical journal papers
and 4 monographs (books) in English (two of them translated to Chinese). He has served as an Associated Editor of IEEE Transa-
ctions on Neural Networks, IEEE Transactions on Signals Processing and as a founding Editor in Chief for Journal Computational
Intelligence and Neuroscience. Currently, his research focus on multiway analysis, tensor networks, brain machine interface,
EEG hyper-scanning, and human to robot interactions. His publications currently report over 22,000 citations (his h-index is 65).