[Seminar] "Tensor Decomposition and Tensor Networks and their applications, especially in Brain Computer Interface and recognition of Human Emotions" by Prof. Andrzej Cichocki
Prof. Andrzej Cichocki
Skolkovo Institute of Science and Technology (SKOLTECH), Moscow
"Tensor Decomposition and Tensor Networks and their applications, especially in Brain Computer Interface and recognition of Human Emotions"
In general, Tensor decomposition (TD) and their generalizations tensor networks (TNs) are promising, and emerging tools in Machine Learning (ML) and big data analysis, since many real life data can be naturally described as higher-order tensors which can be appropriately represented in distributed forms by factors or cores with reduced the number of parameters.
We will also present a brief overview of tensor decomposition and tensor networks architectures and associated learning algorithms and indicate their perspective and potential applications. Special emphasis will be given to feature extraction and classification problems in Brain Computer Interface (BCI) and recognition of human emotions. We graphically illustrate models of Tensor Train, Tensor Ring and Hierarchic Tucker and other related tensor network models for high order tensors.
Tensor Train and Hierarchical Tucker (HT) models will be naturally extended to MERA (Multiscale Entanglement Renormalization Ansatz) models, PEPS/PEPO and other 2D/3D tensor networks, which may inspire novel deep neural networks with improved expressive power.
Andrzej Cichocki received the M.Sc. (with honors), Ph.D. and Dr.Sc. (Habilitation) degrees, all in electrical engineering from Warsaw University of Technology (Poland). He spent several years at University Erlangen (Germany) as an Alexander-von-Humboldt Research Fellow and Guest Professor. He was a Senior Team Leader and Head of the laboratory for Advanced Brain Signal Processing, at RIKEN Brain Science Institute (Japan) and now he is a Professor in the Skolkovo Institute of Science and Technology - SKOLTECH (Russia). He is author of more than 500 technical journal papers and 5 monographs in English (two of them translated to Chinese). He served as Associated Editor of, IEEE Trans. on Signals Processing, IEEE Trans. on Neural Networks and Learning Systems, IEEE Trans on Cybernetics, Journal of Neuroscience Methods and he was as founding Editor in Chief for Journal Computational Intelligence and Neuroscience. Currently, his research focus on multiway blind source separation, tensor decompositions, tensor networks for large-scale optimization problems, and Brain Computer Interface. His publications currently report over 38,000 citations according to Google Scholar, with an h-index of 85. He is Fellow of the IEEE since 2013.