МЕГАГРАНТЫ

Лаборатория "Тензорные сети и глубинное обучение для интеллектуального анализа данных"

О лаборатории

Наименование проекта
Тензорные сети и глубинное обучение для интеллектуального анализа данных

№ договора:

14.756.31.0001

Сайт лаборатории

Наименование организации
Автономная некоммерческая образовательная организация высшего образования "Сколковский институт науки и технологий"

Область научных исследований
Компьютерные и информационные науки

Разработка принципиально новых подходов построения, обучения, использования и хранения параметров глубинных нейронных сетей, позволяющих на порядки снизить вычислительную сложность и объемы памяти, требуемые для работы с сетью, при высоком качестве предсказания.
Анализ архитектуры современных глубинных нейронных сетей (сверточные и рекуррентные нейронные сети, ограниченные машины Больцмана, автокодировщики и т.д.) и выявление их связи с тензорными сетями.
Исследование возможностей и перспектив использования различных тензорных сетей для малорангового (сжатого) представления данных. Разработка новых алгоритмов для тензорных разложений, в том числе, для разложения тензорного поезда (tensor train, TT-разложение).
Применение методов малоранговых тензорных аппроксимаций, в частности, разложения тензорного поезда (tensor train, TT-разложение) и квантизованного разложения тензорного поезда (quantized tensor train, QTT-разложение) к глубинным нейронным сетям для сжатого (малорангового) представления массивов весов сети, а также формулировка новых алгоритмов обучения в рамках используемого малорангового приближения.
Разработка улучшенной вариационной нижней оценки, которая обеспечивает более точный вариационный Байесовский вывод. Создание методов стохастической оптимизации, заточенных под вид этой новой вариационной оценки и исследование их свойств. Ускорение полученных алгоритмов с использованием методов малоранговых тензорных аппроксимаций.
Применение разработанных подходов к ряду прикладных задач, связанных с интеллектуальным анализом данных и машинным обучением.
Разработка методов деблюрринга (устранения размытостей и искажений) изображений на основе глубинного обучения.
Разработка методов быстрого обнаружения предметов и определения их положения в пространстве на основе глубинного обучения.
Разработка мобильных приложений (способных работать на маломощных устройствах, таких как планшеты, сотовые телефоны и фотоаппараты), реализующих полученные новые быстрые алгоритмы для деблюрринга, обнаружения предметов и определения их положения и т.д.
Создание в Автономной некоммерческой образовательной организации высшего профессионального образования «Сколковский институт науки и технологий» (Сколтех) ведущей научной лаборатории и научно-образовательного центра по методам интеллектуального анализа данных и машинного обучения. После завершения проекта лаборатория станет исследовательским центром мирового уровня по данным тематикам исследований.
Подготовка и проведение ряда лекционных курсов по тематике проекта для студентов Сколтеха.
Привлечение к работе в лаборатории студентов (подготовка магистерских дипломных работ) и аспирантов (подготовка кандидатских диссертаций) Сколтеха и других ведущих Российских вузов.
Проведение на базе Сколтеха открытых семинаров и международных конференций по тематике проекта.
Организация международного сотрудничества с ведущими образовательными и научными организациями и проведение соответствующих мероприятий: стажировка/обмен студентами и аспирантами, организация двусторонних встреч с ведущими учеными по направлению исследования и т.д.

Ведущий учёный

cichocki 

ФИО: Чихоцкий Анджей Станислав

 

Дата рождения 08.08.1947

Гражданство
Польша Япония

Ученые степень и звание

Доктор наук

Место работы

Лаборатория обработки сигналов головного мозга, научный институт мозга, RIKEN

Область научных интересов

Область научных интересов Доктора Чихотского А. включает тензорные разложения и факторизации, интеллектуальный анализ данных, оптимизационные задачи в области биомедицинских приложений и т.д.

Достижения и награды

Согласно данным Академии Google, доктор Анджей Чихотский имеет индекс Хирша 70 с числом цитирования работ более чем 27000. Доктор Анджей Чихотский был приглашен в «Council of Canadian Academies Survey of Science and Technology Strengths» как автор научных работ, имеющий наивысший уровень цитирования (входит в топ 1%) в мире по своей предметной области.

Доктор Анджей Чихотский являлся членом редакции (8 журналов) и рецензентом (более 10 журналов) ведущих мировых научных изданий («Journal of Computational Intelligence and Neuroscience», «IEEE Transaction on Neural Networks», «Methods in Neuroscience», «Neural Computation», «Neurocomputing», «Journal of Neural Networks» и т.д.), членом множества технических комитетов международных программ и конференций («IEEE Circuits and Systems Technical Committee for Blind Signal Processing», «Machine Learning for Signal Processing Technical Committee» и т.д.).

Доктор Анджей Чихотский принимал участие в разработке прикладных программных пакетов: Independent Component Analysis LAB, Nonnegative Tensor Factorization LAB, Nonnegative Matrix Factorizations LAB и др. Также он является автором 6 патентов.

1. Zhao Q, Zhou G, Zhang L, Cichocki A, Amari S. Bayesian robust tensor factorization for incomplete multiway data. IEEE Trans. on Neural Networks and Learning Systems 27(4): 736-748 (2016).
2. Zhou G, Cichocki A, Zhang Y, Mandic D. Group Component Analysis for Multi-block Data: Common and Individual Feature Extraction. IEEE Transactions on Neural Networks and Learning Systems, (2)104, pp.310-331 (2016).
3. Zhou G, Zhao Q, Zhang Y, Adali T, Xie S, Cichocki A. Linked Component Analysis from Matrices to High Order Tensors: Applications to Biomedical Data. Proceedings of the IEEE . 104(2): 310-331 (2016).
4. Li J, Li C, Cichocki A. Canonical Polyadic Decomposition with Auxiliary Information for Brain-Computer Interface. IEEE Journal of Biomedical and Health Informatics (accepted).
5. Chen, L., Jin, J., Daly, I., Zhang, Y., Wang, X., and Cichocki, A. (2016). Exploring Combinations of Different Color and Facial Expression Stimuli for Gaze-Independent BCIs. Frontiers in Computational Neuroscience, 10 (2016).
6. Y. Zhang, G. Zhou, Q. Zhao, A. Cichocki, X. Wang Fast nonnegative tensor factorization based on accelerated proximal gradient and low-rank approximation Neurocomputing, (in press, 2016).
7. Nam Y., Koo B, Cichocki A., Choi S. Glossokinetic Potentials for Tongue-Machine Interface. IEEE SMC Magazine. (accepted).
8. Z. Zeng, A. Cichocki, L. Cheng, Y. Xia, X. Hu: Guest Editorial Special Issue on Neurodynamic Systems for Optimization and Applications. IEEE Trans. Neural Netw. Learning Syst. 27(2): 210-213 (2016).

Результаты исследований

Публикации

Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions // Foundations and Trends in Machine Learning.
Cichocki Andrzej, Lee Namgil, Oseledets Ivan, Phan Anh-Huy, Zhao Qibin, Mandic Danilo, others.

Sparse bayesian classification of EEG for brain--computer interface // IEEE Transactions on Neural Networks and Learning Systems.
Zhang Yu, Zhou Guoxu, Jin Jing, Zhao Qibin, Wang Xingyu, Cichocki Andrzej.

Group component analysis for multiblock data: Common and individual feature extraction // IEEE Transactions on Neural Networks and Learning Systems.
Zhou Guoxu, Cichocki Andrzej, Zhang Yu, Mandic Danilo.

Bayesian robust tensor factorization for incomplete multiway data // IEEE Transactions on Neural Networks and Learning Systems.
Zhao Qibin, Zhou Guoxu, Zhang Liqing, Cichocki Andrzej, Amari Shun-Ichi.

Fast nonnegative tensor factorization based on accelerated proximal gradient and low-rank approximation // Neurocomputing.
Zhang Yu, Zhou Guoxu, Zhao Qibin, Cichocki Andrzej, Wang Xingyu.

Improved SFFS method for channel selection in motor imagery based BCI // Neurocomputing.
Qiu Zhaoyang, Jin Jing, Lam Hak-Keung, Zhang Yu, Wang Xingyu, Cichocki Andrzej.

Partitioned Alternating Least Squares Technique for Canonical Polyadic Tensor Decomposition // IEEE Signal Processing Letters.
Tichavsky Petr, Phan Anh-Huy, Cichocki Andrzej.

Discriminative feature extraction via multivariate linear regression for SSVEP-based BCI // IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Wang Haiqiang, Zhang Yu, Waytowich Nicholas, Krusienski Dean, Zhou Guoxu, Jin Jing, Wang Xingyu, Cichocki Andrzej.

Total Variation Regularized Tensor RPCA for Background Subtraction From Compressive Measurements // IEEE Transactions on Image Processing.
Cao Wenfei, Wang Yao, Sun Jian, Meng Deyu, Yang Can, Cichocki Andrzej, Xu Zongben.

Regularized computation of approximate pseudoinverse of large matrices using low-rank tensor train decompositions // SIAM Journal on Matrix Analysis and Applications.
Lee Namgil, Cichocki Andrzej.

Rank-one tensor injection: A novel method for canonical polyadic tensor decomposition // Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on.
Phan Anh-Huy, Tichavsky Petr, Cichocki Andrzej.

A Six-Step Framework on Biomedical Signal Analysis for Tackling Noncommunicable Diseases: Current and Future Perspectives // JMIR Biomedical Engineering.
Elgendi Mohamed, Howard Newton, Lovell Nigel, Cichocki Andrzej, Brearley Matt, Abbott Derek, Adatia Ian.

Tensor ring decomposition. //
Zhao Qibin, Zhou Guoxu, Xie Shengli, Zhang Liqing, Cichocki Andrzej.

Removal of EEG artifacts for BCI applications using fully Bayesian tensor completion // Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on.
Zhang Yu, Zhao Qibin, Zhou Guoxu, Jin Jing, Wang Xingyu, Cichocki Andrzej.

Tensor networks for latent variable analysis. Part I: Algorithms for tensor train decomposition. //
Phan Anh-Huy, Cichocki Andrzej, Uschmajew Andr'e, Tichavsky Petr, Luta George, Mandic Danilo.

An exploration of spatial auditory BCI paradigms with different sounds: music notes versus beeps // Cognitive Neurodynamics.
Huang Minqiang, Daly Ian, Jin Jing, Zhang Yu, Wang Xingyu, Cichocki Andrzej.

Rate of Convergence of the FOCUSS Algorithm // IEEE Transactions on Neural Networks and Learning Systems.
Xie Kan, He Zhaoshui, Cichocki Andrzej, Fang Xiaozhao.

Guest editorial special issue on neurodynamic systems for optimization and applications // IEEE Transactions on Neural Networks and Learning Systems.
Zeng Zhigang, Cichocki Andrzej, Cheng Long, Xia Youshen, Hu Xiaolin.

Effects of Background Music on Objective and Subjective Performance Measures in an Auditory BCI // Frontiers in Computational Neuroscience.
Zhou Sijie, Allison Brendan, Kubler Andrea, Cichocki Andrzej, Wang Xingyu, Jin Jing.

Nonnegative Tensor Train Decompositions for Multi-domain Feature Extraction and Clustering // International Conference on Neural Information Processing.
Lee Namgil, Phan Anh-Huy, Cong Fengyu, Cichocki Andrzej.

Motor Priming as a Brain-Computer Interface // International Conference on Neural Information Processing.
Stewart Tom, Hoshino Kiyoshi, Cichocki Andrzej, Rutkowski Tomasz.

Exploiting ongoing EEG with multilinear partial least squares during free-listening to music // Machine Learning for Signal Processing (MLSP), 2016 IEEE 26th International Workshop on.
Wang Deqing, Cong Fengyu, Zhao Qibin, Toiviainen Petri, Nandi Asoke, Huotilainen Minna, Ristaniemi Tapani, Cichocki Andrzej.

Bayesian CP factorization of incomplete tensor for EEG signal application // Fuzzy Systems (FUZZ-IEEE), 2016 IEEE International Conference on.
Cui Gaochao, Gui Lihua, Zhao Qibin, Cichocki Andrzej, Cao Jianting.

Tensor completion via functional smooth component deflation // Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on.
Yokota Tatsuya, Cichocki Andrzej.

Common and Discriminative Subspace Kernel-Based Multiblock Tensor Partial Least Squares Regression. // AAAI.
Hou Ming, Zhao Qibin, Chaib-draa Brahim, Cichocki Andrzej.

Usefulness of Quasi-L1 Norm-Based Nonnegative Matrix Factorization Algorithm to Estimate Background Signal using Environmental Electromagnetic Field Measurements at ELF Band // IEEJ Transactions on Fundamentals and Materials.
Mouri Motoaki, Takumi Ichi, Yasukawa Hiroshi, Cichocki Andrzej.

Glossokinetic Potentials for a Tongue-Machine Interface: How Can We Trace Tongue Movements with Electrodes? // IEEE Systems, Man, and Cybernetics Magazine.
Nam Yunjun, Koo Bonkon, Cichocki Andrzej, Choi Seungjin.

Optimizing the Face Paradigm of BCI System by Modified Mismatch Negative Paradigm // Frontiers in Neuroscience.
Zhou Sijie, Jin Jing, Daly Ian, Wang Xingyu, Cichocki Andrzej.

Exploring Combinations of Different Color and Facial Expression Stimuli for Gaze-Independent BCIs // Frontiers in Computational Neuroscience.
Chen Long, Jin Jing, Daly Ian, Zhang Yu, Wang Xingyu, Cichocki Andrzej.

Unifying time evolution and optimization with matrix product states // Phys. Rev. B.
Haegeman Jutho, Lubich Christian, Oseledets Ivan, Vandereycken Bart, Verstraete Frank.

Grid-based electronic structure calculations: the tensor decomposition approach // J. Comp. Phys..
Rakhuba M, Oseledets Ivan.

Calculating vibrational spectra of molecules using tensor train decomposition // J. Chem. Phys..
Rakhuba Maxim, Oseledets Ivan.

Iterative representing set selection fo nested cross approximation // Numer. Linear Algebra Appl..
Mikhalev Yu, Oseledets Ivan.

QTT-finite-element approximation for multiscale problems I: model problems in one dimension // Adv. Comp. Math..
Kazeev Vladimir, Oseledets Ivan, Rakhuba Maxim, Schwab Christoph.

"Compress and eliminate" solver for symmetric positive definite sparse matrices. //
Sushnikova Daria, Oseledets Ivan.

Tensor methods and recommender systems // Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery.
Frolov Evgeny, Oseledets Ivan.

Preconditioners for hierarchical matrices based on their extended sparse form // Russ. J. Numer. Anal. Math. Modelling.
Sushnikova Daria, Oseledets Ivan.

Efficient Rectangular Maximal-Volume Algorithm for Rating Elicitation in Collaborative Filtering. //
Fonarev Alexander, Mikhalev Alexander, Serdyukov Pavel, Gusev Gleb, Oseledets Ivan.

A new approach for sparse Bayesian channel estimation in SCMA uplink systems // Wireless Communications & Signal Processing (WCSP), 2016 8th International Conference on.
Struminsky Kirill, Kruglik Stanislav, Vetrov Dmitry, Oseledets Ivan.

A low-rank approach to the computation of path integrals // Journal of Computational Physics.
Litsarev Mikhail, Oseledets Ivan.

What Lies Beneath the Surface: Topological-Shape Optimization With the Kernel-Independent Fast Multipole Method. //
Ostanin Igor, Tsybulin Ivan, Litsarev Mikhail, Oseledets Ivan, Zorin Denis.

Desingularization of bounded-rank matrix sets. //
Khrulkov Valentin, Oseledets Ivan.

Robust discretization in quantized tensor train format for elliptic problems in two dimensions. //
Chertkov Andrei, Oseledets Ivan, Rakhuba M.

Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Recommendations Tasks // Proceedings of the 10th ACM Conference on Recommender Systems.
Frolov Evgeny, Oseledets Ivan.

Machine learning for LC-MS medicinal plants identification // Chemometrics and Intelligent Laboratory Systems.
Nazarenko D, Kharyuk P, Oseledets Ivan, Rodin I, Shpigun O.

Tensor Train Methods for Quantum Molecular Dynamics. //
Oseledets Ivan.

Convergence analysis of projected fixed-point iteration on a low-rank matrix manifold. //
Kolesnikov Denis, Oseledets Ivan.

Texture networks: Feed-forward synthesis of textures and stylized images // Int. Conf. on Machine Learning (ICML).
Ulyanov Dmitry, Lebedev Vadim, Vedaldi Andrea, Lempitsky Victor.

Fast convnets using group-wise brain damage // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
Lebedev Vadim, Lempitsky Victor.

Instance Normalization: The Missing Ingredient for Fast Stylization. //
Ulyanov Dmitry, Vedaldi Andrea, Lempitsky Victor.

Detecting overlapping instances in microscopy images using extremal region trees // Medical Image Analysis.
Arteta Carlos, Lempitsky Victor, Noble Alison, Zisserman Andrew.

Efficient indexing of billion-scale datasets of deep descriptors // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
Babenko Artem, Lempitsky Victor.

Learning deep embeddings with histogram loss // Advances in Neural Information Processing Systems.
Ustinova Evgeniya, Lempitsky Victor.

Counting in the Wild // European Conference on Computer Vision.
Arteta Carlos, Lempitsky Victor, Zisserman Andrew.

DeepWarp: Photorealistic image resynthesis for gaze manipulation // European Conference on Computer Vision.
Ganin Yaroslav, Kononenko Daniil, Sungatullina Diana, Lempitsky Victor.

Parsing Images of Overlapping Organisms with Deep Singling-Out Networks. //
Yurchenko Victor, Lempitsky Victor.

Internet-Based Image Retrieval Using End-to-End Trained Deep Distributions. //
Vakhitov Alexander, Kuzmin Andrey, Lempitsky Victor.

End-to-end Learning of Cost-Volume Aggregation for Real-time Dense Stereo. //
Kuzmin Andrey, Mikushin Dmitry, Lempitsky Victor.

Pairwise Quantization. //
Babenko Artem, Arandjelovi Relja, Lempitsky Victor.

Fast low-cost single element ultrasound reflectivity tomography using angular distribution analysis // Biomedical Imaging (ISBI), 2016 IEEE 13th International Symposium on.
Kuzmin Audrey, Zhang Xiang, Finche Jonathan, Feigin Micha, Anthony Brian, Lempitsky Victor.

Learnable Visual Markers // Advances In Neural Information Processing Systems.
Grinchuk Oleg, Lebedev Vadim, Lempitsky Victor.

Breaking sticks and ambiguities with adaptive skip-gram // Artificial Intelligence and Statistics.
Bartunov Sergey, Kondrashkin Dmitry, Osokin Anton, Vetrov Dmitry.

PerforatedCNNs: Acceleration through elimination of redundant convolutions // Advances in Neural Information Processing Systems.
Figurnov Mikhail, Ibraimova Aizhan, Vetrov Dmitry, Kohli Pushmeet.

Spatially Adaptive Computation Time for Residual Networks. //
Figurnov Michael, Collins Maxwell, Zhu Yukun, Zhang Li, Huang Jonathan, Vetrov Dmitry, Salakhutdinov Ruslan.

Ultimate tensorization: compressing convolutional and FC layers alike. //
Garipov Timur, Podoprikhin Dmitry, Novikov Alexander, Vetrov Dmitry.

Fast Adaptation in Generative Models with Generative Matching Networks. //
Bartunov Sergey, Vetrov Dmitry.

Robust Variational Inference. //
Figurnov Michael, Struminsky Kirill, Vetrov Dmitry.

Deep Part-Based Generative Shape Model with Latent Variables // 27th British Machine Vision Conference (BMVC 2016).
Kirillov Alexander, Gavrikov Mikhail, Lobacheva Ekaterina, Osokin Anton, Vetrov Dmitry.

Tensor Train polynomial models via Riemannian optimization. //
Novikov Alexander, Trofimov Mikhail, Oseledets Ivan.

Dropout-based Automatic Relevance Determination // Bayesian Deep Learning workshop, NIPS.
Molchanov Dmitry, Ashuha Arseniy, Vetrov Dmitry.

Exponential machines. //
Novikov Alexander, Trofimov Mikhail, Oseledets Ivan.

Low-rank approach to the computation of path integrals // J. Comp. Phys..
Litsarev M, Oseledets Ivan.

Compress and eliminate solver for symmetric positive definite sparse matrices. //
Sushnikova Daria, Oseledets Ivan.

Low-Rank Tensor Networks for Dimensionality Reduction and Large-Scale Optimization Problems: Perspectives and Challenges PART 1. //
Cichocki A, Lee N, Oseledets Ivan, Phan Anh-Huy, Zhao Q, Mandic D.

Black-box solver for multiscale modelling using the QTT format // Proc. ECCOMAS.
Oseledets Ivan, Rakhuba Maxim, Chertkov Andrei.

Linked component analysis from matrices to high order tensors: Applications to biomedical data // Proceedings of the IEEE.
Guoxu Zhou, Qibin Zhao, Yu Zhang, T. Adali, Shengli Xie, Cichocki Andrzej.

Editorial: Biomedical Signal Processing: From a Conceptual Framework to Clinical Applications // Proceedings of the IEEE.
Mathias Baumert, Alberto Porta, Cichocki Andrzej.

Coding of faces by tensor components // Journal of Vision.
Lehky Sidney, Phan Anh-Huy, Cichocki Andrzej, Tanaka Keiji.

Numerical CP decomposition of some difficult tensors // Journal of Computational and Applied Mathematics.
Phan Anh-Huy, Cichocki A.

Rate of Convergence of the FOCUSS Algorithm // IEEE Transactions on Neural Networks and Learning Systems.
Xie Kan, He Zhaoshui, Cichocki Andrzej, Fang Xiaozhao.

A new perspective of noise removal from EEG // 8th International IEEE/EMBS Conference on Neural Engineering (NER).
Li Junhua, Li Chao, Thakor Nitish, Cichocki Andrzej, Bezerianos Anastasios.

Neural Networks for Computing Best Rank-One Approximations of Tensors and its Applications // Neurocomputing.
Che Maolin, Cichocki Andrzej, Wei Yimin.

Learning Efficient Tensor Representations with Ring Structure Networks. //
Zhao Qibin, Sugiyama Masashi, Cichocki Andrzej.

Video Denoising Using Low Rank Tensor Decomposition // Ninth International Conference on Machine Vision.
Gui Lihua, Cui Gaochao, Zhao Qibin, Wang Dongsheng, Cichocki Andrzej, Cao Jianting.

An improved P300 pattern in BCI to catch user’s attention // Journal of Neural Engineering.
Jin Jing, Zhang Hanhan, Daly Ian, Wang Xingyu, Cichocki Andrzej.

An augmented Lagrangian algorithm for decomposition of symmetric tensors of order-4 // IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Phan Anh-Huy, Yamagishi Masao, Cichocki Andrzej.

Partitioned Hierarchical alternating least squares algorithm for CP tensor decomposition // IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Phan Anh-Huy, Tichavsky Petr, Cichocki Andrzej.

Robust multilinear tensor rank estimation using higher order singular value decomposition and information criteria // IEEE Transactions on Signal Processing.
Yokota Tatsuya, Lee Namgil, Cichocki Andrzej.

Optimization of Alpha-Beta Log-Det Divergences and their Application in the Spatial Filtering of Two Class Motor Imagery Movements // Entropy.
Thiyam Deepa, Cruces Sergio, Olias Javier, Cichocki Andrzej.

Blind source separation of single channel mixture using tensorization and tensor diagonalization // International Conference on Latent Variable Analysis and Signal Separation.
Phan Anh-Huy, Tichavsky Petr, Cichocki Andrzej.

Sparse Bayesian multiway canonical correlation analysis for EEG pattern recognition // Neurocomputing.
Zhang Yu, Zhou Guoxu, Jin Jing, Zhang Yangsong, Wang Xingyu, Cichocki Andrzej.

Optimized motor imagery paradigm based on imagining Chinese characters writing movement // IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Qiu Zhaoyang, Allison Brendan, Jin Jing, Zhang Yu, Wang Xingyu, Li Wei, Cichocki Andrzej.

Fundamental tensor operations for large-scale data analysis using tensor network formats // Multidimensional Systems and Signal Processing.
Lee Namgil, Cichocki Andrzej.

A New Generation of Brain-Computer Interfaces Driven by Discovery of Latent EEG-fMRI Linkages Using Tensor Decomposition // Frontiers in neuroscience.
Deshpande Gopikrishna, Rangaprakash D, Oeding Luke, Cichocki Andrzej, Hu Xiaoping.

A New Generation of Brain-Computer Interfaces Driven by Discovery of Latent EEG-fMRI Linkages using Tensor Decomposition // Frontiers in Neuroscience.
Deshpande Gopikrishna, Rangaprakash D, Oeding Luke, Cichocki Andrzej, Hu Xiaoping.

Fundamental tensor operations for large-scale data analysis using tensor network formats // Multidimensional Systems and Signal Processing.
Lee Namgil, Cichocki Andrzej.

Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Potential Applications and Future Perspectives // Foundations and Trends in Machine Learning.
Cichocki Andrzej, Phan Anh-Huy, Zhao Qibin, Lee Namgil, Oseledets Ivan, Sugiyama Masashi, Mandic Danilo.

Tensor Networks for Dimensionality Reduction and Large-Scale Optimization: Part 1 Low-Rank Tensor Decompositions // Foundations and Trends in Machine Learning.
Cichocki Andrzej, Lee Namgil, Oseledets Ivan, Phan Anh-Huy, Zhao Qibin, Mandic Danilo.

An improved P300 pattern in BCI to catch user's attention // Journal of Neural Engineering.
Jin Jing, Zhang Yu, Daly Ian, Wang Xingyu, Cichocki Andrzej.

Non-orthogonal tensor diagonalization // Signal Processing.
Petr Tichavsky, Phan Anh-Huy, Cichocki Andrzej.

The Effects of Audiovisual Inputs on Solving the Cocktail Party Problem in the Human Brain: An fMRI Study // Cerebral Cortex.
Li Y., Wang F., Chen Y., Cichocki Andrzej, Sejnowski T.

Scalable topology optimization with the kernel-independent fast multipole method // Engineering Analysis with Boundary Elements.
Ostanin Igor, Tsybulin Ivan, Litsarev Mikhail, Oseledets Ivan, Zorin Denis.

Alternating least squares as moving subspace correction Authors. //
Oseledets Ivan, Rakhuba Maxim, Uschmajew Andre.

AA-ICP: Iterative Closest Point with Anderson Acceleration. //
Pavlov AL, Ovchinnikov GV, Derbyshev D, Tsetserukou D, Oseledets Ivan.

Art of singular vectors and universal adversarial perturbations. //
Khrulkov Valentin, Oseledets Ivan.

Regularization of topology optimization problem by the FEM a posteriori error estimator. //
Pimanov Vladislav, Oseledets Ivan.

Robust regularization of topology optimization problems with a posteriori error estimators. //
Ovchinnikov GV, Zorin D, Oseledets Ivan.

Deep multi-frame face hallucination for face identification. //
Ustinova Evgeniya, Lempitsky Victor.

Photorealistic Monocular Gaze Redirection Using Machine Learning // IEEE Transactions on Pattern Analysis and Machine Intelligence.
Kononenko Daniil, Ganin Yaroslav, Sungatullina Diana, Lempitsky Victor.

Set2Model networks: Learning discriminatively to learn generative models // Computer Vision and Image Understanding.
Vakhitov Alexander, Kuzmin Andrey, Lempitsky Victor.

Riemannian Optimization for Skip-Gram Negative Sampling // Proc. ACL-2017.
Fonarev Alexander, Aleksey Grinchuk, Gusev Gleb, Serdyukov Pavel, Oseledets Ivan.

Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis // Proc. CVPR-2017 .
Ulyanov Dmitry, Vedaldi Andrea, Lempitsky Victor.

Variational Dropout Sparsifies Deep Neural Networks // Proc.ICML-2017.
Molchanov Dmitry, Ashukha Arsenii, Vetrov Dmitry.

Structured Bayesian Pruning via Log-Normal Multiplicative Noise. //
Neklyudov Kirill, Molchanov Dmitry, Ashukha Arsenii, Vetrov Dmitry.

Adversarial Generator-Encoder Networks. //
Ulyanov Dmitry, Vedaldi Andrea, Lempitsky Victor.

Escape from Cells: Deep Kd-Networks for The Recognition of 3D Point Cloud Models. //
Klokov Roman, Lempitsky Victor.

Simple non-extensive sparsification of the hierarchical matrices. //
Sushnikova Daria, Oseledets Ivan.

Time-and memory-efficient representation of complex mesoscale potentials // Journal of Computational Physics.
Drozdov Grigory, Ostanin Igor, Oseledets Ivan.

Vico-Greengard-Ferrando quadratures in the tensor solver for integral equations. //
Khrulkov Valentin, Rakhuba Maxim, Oseledets Ivan.

Fast topological-shape optimization with boundary elements in two dimensions // Russian Journal of Numerical Analysis and Mathematical Modelling.
Ostanin Igor, Zorin Denis, Oseledets Ivan.

Jacobi-Davidson method on low-rank matrix manifolds. //
Rakhuba Maxim, Oseledets Ivan.

Parallel Optimization With Boundary Elements And Kernel Independent Fast Multipole Method // International Journal of Computational Methods and Experimental Measurements.
Ostanin Igor, Zorin Denis, Oseledets Ivan.

Fast, memory efficient low-rank approximation of SimRank // Journal of Complex Networks.
Oseledets Ivan, Ovchinnikov G, Katrutsa A.

Optimized motor imagery paradigm based on imagining Chinese characters writing movement // IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Qiu Zhaoyang, Allison Brendan, Jin Jing, Zhang Yu, Wang Xingyu, Li Wei, Cichocki Andrzej.

Numerical CP Decomposition of Some Difficult Tensors // Journal of Computational and Applied Mathematics.
Phan Anh-Huy, Cichocki A.

Robust multilinear tensor rank estimation using higher order singular value decomposition and information criteria // IEEE Transactions on Signal Processing.
Yokota Tatsuya, Lee Namgil, Cichocki Andrzej.

Canonical Polyadic Decomposition With Auxiliary Information for Brain--Computer Interface // IEEE Journal of Biomedical and Health Informatics.
Li Junhua, Li Chao, Cichocki Andrzej.


| 2018
Expressive power of recurrent neural networks // International Conference on Learning Representations.

Khrulkov Valentin, Novikov Alexander, Oseledets Ivan.

| 2018
Art of singular vectors and Universal Adversarial Perturbations // The IEEE Conference on Computer Vision and Pattern Recognition.

Khrulkov Valentin, Oseledets Ivan.

| 2018
Geometry score: A method for comparing Generative Adversarial Networks // International Conference on Machine Learning.

Khrulkov Valentin, Oseledets Ivan.

| 2018
Deep image prior // Conference on Computer Vision and Pattern Recognition.

Ulyanov Dmitry, Vedaldi Andrea, Lempitsky Victor.

| 2018
Image manipulation with perceptual discriminators // European Conference on Computer Vision.

Sungatullina Diana, Zakharov E., Ulyanov Dmitry, Lempitsky Victor.

| 2018
Latent convolutional models // (under review on NIPS 2018).

ShahRukh Athar, Evgeny Burnaev, Lempitsky Victor.

| 2018
Fundamental tensor operations for large-scale data analysis using tensor network formats // Multidimensional Systems and Signal Processing.

Lee Namgil, Cichocki Andrzej.

| 2018
Sparse group representation model for motor imagery EEG classification // IEEE Journal of Biomedical and Health Informatics.

Yong Jiao, Yu Zhang, Xun Chen, Erwei Yin, Jing Jin, Xing yu Wang, Cichocki Andrzej.

| 2018
A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update // Journal of Neural Engineering.

Lotte F., Bougrain L., Cichocki Andrzej, Clerc M., Congedo M., Rakotomamonjy A., Yger F.

| 2018
Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces // Expert Systems with Applications.

Yu Zhang, Yu Wang, Guoxu Zhou, Jing Jin, Bei Wang, Xingyu Wang, Cichocki Andrzej.

| 2018
Whole brain fMRI pattern analysis based on tensor neural network // IEEE Access.

Xiaowen Xu, Qiang Wu, Shuo Wang, Ju Liu, Jiande Sun, Cichocki Andrzej.

| 2018
EmotionMeter: A multimodal framework for recognizing human emotions // IEEE Transactions on Cybernetics.

Wei-Long Zheng, Wei Liu, Yifei Lu, Bao-Liang Lu, Cichocki Andrzej.

| 2018
Information theoretic approaches for motor-imagery BCI systems: Review and experimental comparison // Entropy.

Rubén Martín-Clemente, Javier Olias, Deepa Beeta Thiyam, Cichocki Andrzej, Sergio Cruces.

| 2018
Subliminal Priming – state of the art and future perspectives // Behavioral sciences (Basel, Switzerland).

Mohamed Elgendi, Parmod Kumar, Skye Barbic, Newton Howard, Derek Abbott, Cichocki Andrzej.

| 2018
Comparative study on the classification methods for breast cancer diagnosis // Bulletin of the Polish Academy of Sciences.

Y. Qiu, G. Zhou, Q. Zhao, Cichocki Andrzej.

| 2018
Brain-Computer Interface with corrupted EEG data: A Tensor Completion Approach // Cognitive Computation.

Sole-Casals J., Caiafa C. F., Zhao Q., Cichocki Andrzej.

| 2018
Desingularization of bounded-rank matrix sets // SIAM Journal on Matrix Analysis and Applications.

Khrulkov Valentin, Oseledets Ivan.

| 2018
Exponential machines // Bulletin of the Polish Academy of Sciences.

Novikov Alexander, Trofimov Mikhail, Oseledets Ivan.

| 2018
Speeding-up convolutional neural networks: A survey // Bulletin of the Polish Academy of Sciences.

Lebedev Vadim, Lempitsky Victor.

| 2018
Fast Multispectral Deep Fusion Networks // Bulletin of the Polish Academy of Sciences.

Engeny Burnaev, V. Osin.

| 2018
Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces // Expert Systems with Applications.

Zhang Y., Wang Y., Zhou G., Jin J., Wang B., Wang X., Cichocki Andrzej.

| 2018
A Robust PCA approach with noise structure learning and spatial-spectral low-rank modeling for Hyperspectral Image Restoration // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

W. Cao, K. Wang, G. Han, J. Yao, Cichocki Andrzej.

| 2018
Error preserving correction for CPD and bounded-norm CPD // IEEE Transaction on Signal Processing.

Phan Anh-Huy, Tichavsky Petr, Cichocki Andrzej.

| 2018
Learning the hierarchical parts of objects by deep non-smooth nonnegative matrix factorization // IEEE Access.

J. Yu, G. Zhou, Cichocki Andrzej, S. Xie.

| 2018
Effect of a combination of flip and zooming stimuli on the performance of a visual brain-computer interface for spelling // Biomedical Engineering/Biomedizinische Technik.

Cheng J., Jin J., Daly I., Zhang Y., Wang B., Wang X., Cichocki Andrzej.

| 2018
Combining behavior and EEG analysis for exploration of dynamic effects of ADHD treatment in animal models // Journal of Neuroscience Methods.

Jurica P., Struzik Z.R., Li J., Horiuchi M., Hiroyama S., Takahara Y., Nishitomi K., Ogawa K., Cichocki Andrzej.

| 2018
Visualization and sonification of long-term epilepsy electroencephalogram monitoring // Journal of Medical and Biological Engineering.

Lin J.W., Chen W., Shen C.P., Chiu M.J., Kao Y.H., Lai F., Zhao Q., Cichocki Andrzej.

Back to top