- Skoltech:
- About
- Admissions
- Education
- About Skoltech Education
- MSc Studies
- MSc Programs
- Advanced Manufacturing Technologies
- Data Science
- Internet Of Things & Wireless Technologies
- Advanced Computational Science
- Energy Systems
- Life Sciences
- Mathematical and Theoretical Physics
- Materials Science
- Photonics and Quantum Materials
- Engineering Systems
- Petroleum Engineering
- Applied Computational Mechanics

- Independent Study Period
- Innovation Workshop
- Industrial Immersion
- Academic Mobility
- MSc Academic Calendar 2022-2023
- MSc Academic Calendar 2023-2024

- MSc Programs
- PhD Studies
- Course Catalog
- Schedule
- Resources
- Library
- Contacts

- Research
- Innovation
- Faculty
- Industry
- Student Life
- Colloquia
- Donate

Full Professor, Head of the Laboratory of Intelligent Signal and Image Processing

**Laboratory of Intelligent Signal and Image Processing**

**Center for Artificial Intelligence Technology**

Head of Research Group on Signal Processing

Associate editor of IEEE Transactions on Cybernetics (Impact Factor 11.448)

Anh-Huy Phan received the Ph.D. degree from the Kyushu Institute of Technology, Kitakyushu, Japan, in 2011.

From October 2007 to March 2018, he was a Research Scientist with the Laboratory for Advanced Brain Signal Processing, Brain Science Institute (BSI), RIKEN, Wako, Japan, from April 2012 to April 2015, a Visiting Research Scientist with the TOYOTA Collaboration Center, BSI-RIKEN.

He was appointed as an Assistant Professor in May 2018, and since June, 2020, he has served as an Associate Professor with the Center for Computational and Data-Intensive Science and Engineering, and Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia. He was a visiting scientist with Brain Science Institute, RIKEN, Japan, and a Visiting Associate Professor with the Tokyo University of Agriculture and Technology (TUAT), Fuchu, Japan.

Prof. Phan is associate editor of the IEEE Transactions on Cybernetics (Impact Factor—11.448)

Prof. Phan received the Best Paper Awards for articles in the IEEE SPM in 2018 and the ICONIP in 2016 and the Outstanding Reviewer Award for maintaining the prestige of ICASSP 2019.

Prof. Phan was a project leader of 5 joint projects with Huawei for

– Compression and acceleration of convolutional neural networks (2019-2020)

– Separation of signals in uplink system (2020- )

– E2E image/video compression (2022 – )

– Human intention prediction (2022 – )

– Efficient visual transformer (2022 – )

His research interests include multilinear algebra, tensor computation, tensor networks, nonlinear system, blind source separation, and brain–computer interface.

___

– 2021, Our two papers appear in the special issue in IEEE Journal of Selected Topics in Signal Processing

Adaptive Rank Selection for Tensor Ring Decomposition

F Sedighin, A Cichocki, AH Phan

IEEE Journal of Selected Topics in Signal Processing 15 (3), 454-463

P Tichavský, AH Phan, A Cichocki

IEEE Journal of Selected Topics in Signal Processing 15 (3), 550-559

**Google Scholar: **https://scholar.google.co.jp/citations?user=pJb7n9EAAAAJ&hl=en&oi=ao

**Researchgate: **https://www.researchgate.net/profile/Anh_Huy_Phan

Conduct research on the following main projects • o Develop robust algorithms with low computational costs for various low-rank tensor decompositions of large-scale data, including the Candecomp/Parafac, Tucker tensor decompositions, low-rank tensor deconvolution, tensor diagonalization, Kronecker tensor decomposition, tensor deflation, feature extraction for multiway data. o We contributed state-of-the-art algorithms to the tensor analysis, especially for the Candecomp/Parafac tensor decomposition. Source codes of the developed algorithms are provided in the package TENSORBOX. • • • • o Early detection of Alzheimer disease |

List of full publications at **Google Scholar: **https://scholar.google.co.jp/citations?user=pJb7n9EAAAAJ&hl=en&oi=ao

**SELECTED PUBLICATIONS**

[1] Cichocki and **A.-H. Phan**. “Fast local algorithms for large-scale nonnegative matrix and tensor factorizations”. IEICE (invited paper), E92-A(3):708–721, March 2009.https://pdfs.semanticscholar.org/4229/f467b059188fc7a1234016a3c80557fa7df0.pdf

[2] **A.-H. Phan **and A. Cichocki: “Tensor Decompositions for Feature Extraction and Classification of High Dimensional Datasets”, Nonlinear Theory and Its Applications, IEICE (invited paper) October 2010, 1 (1): 37-68. https://www.jstage.jst.go.jp/article/nolta/1/1/1_1_37/_article/-char/ja/

[3] **A.-H. Phan**, P. Tichavsky and A. Cichocki, “Tensor deflation for CANDECOMP/PARAFAC. Part 1: alternating subspace update algorithm”, *IEEE Transactions on Signal Processing*, 63(12), pp. 5924-5938, 2015. http://ieeexplore.ieee.org/abstract/document/7163349/

[4] **A.-H. Phan**, P. Tichavsky and A. Cichocki, “Tensor deflation for CANDECOMP/PARAFAC. Part 2: Initialization and error analysis”, *IEEE Transactions on Signal Processing*, 63(12), pp. 5939-5950, 2015. http://ieeexplore.ieee.org/document/7163358/

[5] **A.-H. Phan**, P. Tichavský, A. Cichocki: “Low complexity damped Gauss-Newton algorithms for parallel factor analysis”, SIAM J. Matrix Analysis and Applications 34(1): 126-147, 2013. http://epubs.siam.org/doi/abs/10.1137/100808034/

**Monographs, Books
**[6] A. Cichocki, N. Lee, I. Oseledets,

[7] A. Cichocki, **A.-H. Phan**, Q. Zhao, N. Lee, I. Oseledets, M. Sugiyama and D. Mandic. “Tensor Networks for Dimensionality Reduction and Large-Scale Optimization. Part 2: Applications and Future Perspectives”, Foundations and Trends in Machine Learning, vol. 9, no. 6 (2016) 431-673.

[8] A. Cichocki, R. Zdunek, **A.-H. Phan**, and S. Amari. *Non-negative Matrix and Tensor Factorizations Applications to Exploratory Multi-way Data Analysis and Blind Source Separation*. John Wiley, New York, 2009.

**Patent
**A. Cichocki,

**Reviewed Journal Publications **

[10] **A. -H. Phan**, P. Tichavský, and A. Cichocki, “Error preserving correction for CPD and bounded-norm CPD” , arXiv preprint arXiv: 1709.08349, 2017.

[11] **A. -H. Phan**, P. Tichavský, and A. Cichocki, “Best rank-one tensor approximation and parallel update algorithm for CPD”, arXiv preprint arXiv: 1709.08336, 2017.

[12] **A. -H. Phan**, P. Tichavský, and A. Cichocki, “Tensor networks for LVA. Part III: CPD of high order tensors”, arXiv preprint, 2017.

[13] **A. -H. Phan**, M. Yamagashi, D. Mandic and A. Cichocki, “Quadratic programming over ellipsoids and its applications to constrained linear regression and tensor decomposition”, arXiv preprint, 2017.

[14] P. Tichavský, **A. -H. Phan**, and A. Cichocki, “Non-orthogonal tensor diagonalization”, Signal Processing 138 (2017), pp. 313–320.

[15] P. Tichavský, **A. -H. Phan**, and A. Cichocki, “Numerical CP decomposition of some difficult tensors”, Journal of Computational and Applied Mathematics, vol. 317, pp. 362–370, 2017.

[16] P. Tichavsky, **A.-H. Phan**, and A. Cichocki, “Partitioned alternating least squares technique for canonical polyadic tensor decomposition,” IEEE Signal Processing Letters, peer review, vol. 23, no. 7, pp. 993–997, July 2016.

[17] **A.-H. Phan**, A. Cichocki, A. Uschmajew, P. Tichavsky, G. Luta, D. Mandic, Tensor networks for latent variable analysis. Part I: Algorithms for tensor train decomposition, arXiv preprint arXiv:1609.09230

[18] **A.-H. Phan**, P. Tichavsky and A. Cichocki, “Tensor deflation for CANDECOMP/PARAFAC. Part 1: alternating subspace update algorithm”, *IEEE Transactions on Signal Processing*, 63(12), pp. 5924-5938, 2015.

[19] **A.-H. Phan**, P. Tichavsky and A. Cichocki, “Tensor deflation for CANDECOMP/PARAFAC. Part 2: Initialization and error analysis”, *IEEE Transactions on Signal Processing*, 63(12), pp. 5939-5950, 2015.

[20] **A.-H. Phan**, P. Tichavsky and A. Cichocki, “Tensor deflation for CANDECOMP/PARAFAC. Part 3: Rank splitting”, ArXiv e-prints 2015, [Online]. Available: http://arxiv.org/abs/1506.04971.

[21] A. Cichocki, D. Mandic, **A.-H. Phan**, C. Caiafa, G. Zhou, Q. Zhao and L. De Lathauwer, “Tensor decompositions for signal processing applications from two-way to multiway component analysis”, *IEEE Signal Processing Magazine*, peer review, 32 (2), pp. 145–163, 2015.

[22] R. Zdunek, **A.-H. Phan **and A. Cichocki, “Image classification with nonnegative matrix factorization based on spectral projected gradient”, P. Koprinkova-Hristova, et al. (eds.), *Artificial Neural Networks*, Springer Series in Bio-/Neuroinformatics, pp. 31-50, 2015.

[23] **A.-H. Phan**, P. Tichavský, A. Cichocki: “Fast alternating algorithms for high dimensional CANDECOMP/PARAFAC tensor factorization”, *IEEE Transactions on Signal Processing*, 2013, 61 (19), 4834-4846. 2013.

[24] **A.-H. Phan**, P. Tichavský, A. Cichocki: “CANDECOMP/PARAFAC decomposition of high-order tensors through tensor reshaping”, *IEEE Transactions on Signal Processing*, 61 (19), 4847 – 4860. 2013.

[25] **A.-H. Phan**, P. Tichavský, A. Cichocki: “Low complexity damped Gauss-Newton algorithms for parallel factor analysis”, SIAM J. Matrix Analysis and Applications 34(1): 126-147, 2013.

[26] P. Tichavský**, A.-H. Phan**, Z. Koldovský, “Cramer-Rao induced bounds for CANDECOMP/PARAFAC tensor decomposition”, *IEEE Transactions on Signal Processing *61(8): 1986-1997, 2013.

[27] Z. Koldovský, P. Tichavský, **A.-H. Phan**, A. Cichocki, “A two-stage MMSE beamformer for underdetermined signal separation”, *IEEE Signal Processing Letters*, 20 (12), 1227-1230, 2013.

[28] F. Cong, **A.-H. Phan**, P. Astikainen, Q. Zhao, Q. Wu, J. K. Hietanen, T. Ristaniemi, A. Cichocki: “Multi-domain feature extraction for small event-related potentials through nonnegative multi-way array decomposition from low dense array EEG”. International Journal of Neural Systems. 23(2), 2013.

[29] F. Cong, **A.H. Phan**, Q. Zhao, T. Huttunen-Scott, J. Kaartinen, T. Ristaniemi, H. Lyytinen, and A. Cichocki , “Benefits of multi-domain feature of mismatch negativity extracted by nonnegative tensor factorization from EEG collected by low density array”, International Journal of Neural Systems, 22(6), 2012.

[30] **A.-H. Phan**, A. Cichocki: “Seeking an appropriate alternative least squares algorithm for nonnegative tensor factorizations”. Neural Computing and Applications, 22(6) (2012).

[31] **A.-H. Phan**, A. Cichocki: “Extended HALS algorithm for nonnegative tucker decomposition and its applications for multi-way analysis and classification”, Neurocomputing 74(11): 1956-1969, 2011.

[32] **A.-H. Phan **and A. Cichocki: “PARAFAC algorithms for large-scale problems”, Neurocomputing, 74(11): 1970-1984, 2011.

[33] **A.H Phan **and A. Cichocki: “Tensor Decompositions for Feature Extraction and Classification of High Dimensional Datasets”, Nonlinear Theory and Its Applications, IEICE (invited paper) October 2010, 1 (1): 37-68.

[34] **A.-H. Phan**, A. Cichocki, and T. Vu-Dinh, “Nonnegative DEDICOM based on tensor decompositions for social networks exploration”, ICONIP & Australian Journal of Intelligent Information Processing Systems , vol. 12, no. 1, pp 10-15, 2010.

[35] R. Zdunek**, A.-H. Phan**, and A. Cichocki, “Damped Newton iterations for nonnegative matrix factorization”, ICONIP & Australian Journal of Intelligent Information Processing Systems, vol. 12, no. 1, pp 16-22, 2010.

[36] Cichocki and **A.-H. Phan**. “Fast local algorithms for large-scale nonnegative matrix and tensor factorizations”. *IEICE (invited paper)*, E92-A(3):708–721, March 2009.

[37] A.Cichocki, Y. Washizawa, T. Rutkowski, H. Bakardjian, **A.-H. Phan**, S. Choi, H. Lee, Q. Zhao, L. Zhang, and Y. Li. “Noninvasive BCIs: Multiway signal-processing array decompositions”. *IEEE Computer*, 41(4):34–42, 2008.

**Peer-reviewed International Conference Papers Published in Proceedings **

[38] P. Tichavskysky, **A.-H. Phan **and A. Cichocki, Under-Determined Tensor Diagonalization for Decomposition of Difficult Tensors, CAMSAP 2017 – 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, pp. 263-266.

[39] **A.-H. Phan**, P. Tichavsk., and A. Cichocki, Blind source separation of single-channel mixture using tensorization and tensor diagonalization, 2017, International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2017), Lecture Notes in Computer Science, vol. 10169, p. 36-46, 2017.

[40] **A.-H. Phan**, M. Yamagishi, and A. Cichocki, An augmented Lagrangian algorithm for decomposition of symmetric tensors of order-4, 2017, IEEE International Conference on Acoustics, Speech and Signal Processing, 2547-2551.

[41] **A.-H. Phan**, P. Tichavsk., and A. Cichocki, Partitioned hierarchical alternating least squares algorithm for CP tensor decomposition, 2017, IEEE International Conference on Acoustics, Speech and Signal Processing, 2542-2546.

[42] N. Lee, **A.-H. Phan**, F. Cong, A. Cichocki, Nonnegative tensor train decompositions for multi-domain feature extraction and clustering, International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, vol. 9949, pp.87-95, 2016 (best paper award).

[43] **A.-H. Phan**, P. Tichavsk. and A. Cichocki, Rank-one tensor injection: a novel method for canonical polyadic tensor decomposition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), peer review, pp. 2549-2553, 2016.

[44] **A. -H. Phan **, P. Tichavsk., and A. Cichocki, Rank splitting for CANDECOMP/PARAFAC, in Latent Variable Analysis and Signal Separation 12th International Conference, LVA/ICA, Lecture Notes in Computer Science, vol. 9237, pp.31-40, Springer, 2015.

[45] **A. -H. Phan **, P. Tichavsk., and A. Cichocki, “Low rank tensor deconvolution”, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), peer review, pp. 2169 – 2173, 2015.

[46] P. Tichavsk., **A.-H. Phan**, and A. Cichocki, “Two-sided diagonalization of order-three tensors”, in 23rd European Signal Processing Conference (EUSIPCO), peer review, pp. 2169–2173 pp-998-1002, 2015.

[47] **A.-H. Phan**, P. Tichavsk., and A. Cichocki, “Deflation method for CANDECOMP/PARAFAC tensor decomposition”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), peer review, pp. 6736-6740, 2014.

[48] **A.-H. Phan**, A. Cichocki, and P. Tichavsk. , “On fast algorithm for Tucker decomposition with orthogonality constraints”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), peer review, pp. 6766–6770, 2014.

[49] R. Zdunek**, A.-H. Phan**, A. Cichocki, GNMF with Newton-Based Methods, Artificial Neural Networks and Machine Learning–ICANN, 2013, Lecture Notes in Computer Science, vol. 8131, pp.90-97.

[50] P. Tichavsk., **A.-H. Phan**, A. Cichocki, A further improvement of a fast damped GAUSS-NEWTON algorithm for CANDECOMP/PARAFAC tensor decomposition, Proc. of IEEE Int. Conf. Acoustics, Speech, Signal Processing,

ICASSP, pp.5964-5968, 2013.

[51] A. J. Brockmeier, J. C Principe, **A.-H. Phan**, A. Cichocki, A greedy algorithm for model selection for tensor decompositions, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6113-6117, 2013.

[52] **A.-H. Phan**, A. Cichocki, Petr Tichavsk., R. Zdunek and S. Lehky, From basis components to complex structural patterns, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3228-3232, 2013.

[53] **A.-H. Phan**, A. Cichocki, P. Tichavsk., G. Luta, A. Brockmeier, Tensor completion through multiple Kronecker product decomposition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3233-3237, 2013.

[54] F. Cong , **A.-H. Phan**, Q. Zhao, Q. Wu, T. Ristaniemi , A. Cichocki, Feature extraction by nonnegative Tucker decomposition from EEG data including testing and training observations. International Conference on Neural Information Processing (ICONIP) 2012, Lecture Notes in Computer Science, vol. 7665, pp. 166-173.

[55] **A.-H. Phan**, A. Cichocki, P. Tichavsk., Z. Koldovsk.: On connection between the convolutive and ordinary nonnegative matrix factorizations. International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Lecture Notes in Computer Science, vol 7191, 2012: 288-296.

[56] **A.-H. Phan**, A. Cichocki, P. Tichavsk., D. P. Mandic, K. Matsuoka: On Revealing Replicating Structures in Multiway Data: A novel tensor decomposition approach. International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Lecture Notes in Computer Science, vol 7191, 2012: 297-305.

[57] F. Cong, **A.-H. Phan**, P. Astikainen, Q. Zhao, J. K. Hietanen, T. Ristaniemi, A. Cichocki: Multi-domain Feature of Event-Related Potential Extracted by Nonnegative Tensor Factorization: 5 vs 14 Electrodes EEG Data. LVA/ International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Lecture Notes in Computer Science, vol 7191, 2012: 502-510.

[58] Z. Koldovsk., **A.-H. Phan**, P. Tichavsk., and A. Cichocki, “A treatment of EEG motor imagery data by underdetermined blind source separation,” 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO), Bucharest, 2012, pp. 1484-1488.

[59] F. Cong, **A.-H. Phan**, Q. Zhao, A. K. Nandi, V. Alluri, P. Toiviainen, H. Poikonen, M. Huotilainen, A. Cichocki, T. Ristaniemi. Analysis of ongoing EEG

elicited by natural music stimuli using nonnegative tensor factorization. 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO), Bucharest, 2012, pp. 494-498.

[60] **A.-H. Phan**, P. Tichavsk., A. Cichocki, and Z. Koldovsk., Low-rank blind nonnegative matrix deconvolution, Proc. of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1893-1896, ISBN: 978-1-4673-0044-5, Kyoto, Japan, March 2012.

[61] A. Onishi, **A.-H. Phan**, K. Matsuoka, A. Cichocki, Tensor classification for P300-based brain computer interface . In: Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 581-584 (2012).

[62] **A.-H. Phan**, A. Cichocki, K. Matsuoka, and J. Cao, Novel hierarchical ALS algorithm for nonnegative tensor factorization. 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp: 1984-1987, 2011.

[63] **A.-H. Phan**, P. Tichavsk., A. Cichocki, Fast damped Gauss-Newton Algorithm for sparse and nonnegative tensor factorization. 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp: 1987-1991, 2011.

[64] **A.-H. Phan**, P. Tichavsk., A. Cichocki, Levenberg–Marquardt algorithm for nonnegative TUCKER decomposition. 2011 IEEE Statistical Signal Processing Workshop (SSP), Nice, 2011, pp. 665-668.

[65] Z. Koldovsk., P. Tichavsk. and **A.-H. Phan**, Stability analysis and fast damped-Gauss-Newton algorithm for INDSCAL tensor decomposition, 2011 IEEE Statistical Signal Processing Workshop (SSP), Nice, 2011, pp. 581-584.

[66] **A.-H. Phan**, A. Cichocki, R. Zdunek, and T. Vu Dinh, Novel alternating least squares algorithm for nonnegative matrix and tensor factorizations. International Conference on Neural Information Processing (ICONIP) 2010, Lecture Notes in Computer Science, vol. 6443, pp. 262-269.

[67] **A.-H. Phan**, A. Cichocki, and T. Vu-Dinh, A tensorial approach to single trial recognition for brain-computer interface. The 2010 International Conference on Advanced Technologies for Communications, Ho Chi Minh City, 2010, pp. 138-141.

[68] **A.-H. Phan**, A. Cichocki, and T. Vu-Dinh, Classification of scenes based on multiway feature extraction. The 2010 International Conference on Advanced Technologies for Communications, Ho Chi Minh City, 2010, pp. 142-145.

[69] F. Cong, I. Kalyakin, **A.-H. Phan**, A. Cichocki, T. Huttunen-Scott, H. Lyytinen, T. Ristaniemi: Extract mismatch negativity and P3a through two-dimensional nonnegative decomposition on time-frequency represented event-related potentials. Advances in Neural Networks. ISNN 2010. Lecture Notes in Computer Science, vol 6064, pp. 385-391.

[70] F. Cong, **A.-H. Phan**, H. Lyytinen, T. Ristaniemi, A. Cichocki, Classifying healthy children and children with attention deficit through features derived from sparse and nonnegative tensor factorization using event-related potential. International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Lecture Notes in Computer Science, vol 6365, pp. 620-628, 2010.

[71] F. Cong, **A.-H. Phan**, A. Cichocki, H. Lyytinen and T. Ristaniemi, Identical Fits of nonnegative matrix/tensor factorization may correspond to different extracted event-related potentials, Proc. International Joint Conference on Neural Networks 2010 (IEEE World Congress on Computational Intelligence), Barcelona, Spain, July 18-23, 2010, pp. 2260-2264.

[72] S. Sanei, **A.-H. Phan**, J-L. Lo, V. Abolghasemi, A. Cichocki. A compressive sensing approach for progressive transmission of images. Digital Signal Processing, 2009, 16th International Conference on, 5-7 July 2009, page(s):1 – 5.

[73] **A.-H. Phan **and A. Cichocki. Analysis of interactions among hidden components for Tucker model. Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference, pp. 154-159.

[74] **A.-H. Phan **and A. Cichocki. Local learning rules for nonnegative Tucker decomposition. Lecture Notes in Computer Science, vol. 5863, pp. 538-545, 2009.

[75] **A.-H. Phan **and A. Cichocki. Advances in PARAFAC using parallel block decomposition. International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, vol. 5863, pp. 323-330, 2009.

[76] Q. Zhao, C. F. Caiafa, A. Cichocki, L. Zhang, and **A.-H. Phan**. Slice oriented tensor decomposition of EEG data for feature extraction in space, frequency and time domains. International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, 2009, vol.5863, 221-228, 2009.

[77] **A.-H. Phan **and A. Cichocki. Fast nonnegative tensor factorization for very large-scale problems using two-stage procedure. 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Aruba, Dutch Antilles, 2009, pp. 297-300.

[78] **A.-H. Phan **and A. Cichocki. Block decomposition for very large-scale nonnegative tensor factorization. 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Aruba, Dutch Antilles, 2009, pp. 316 – 319.

[79] A. Cichocki, **A.-H. Phan**, and C. Caiafa. Flexible HALS algorithms for sparse non-negative matrix/tensor factorization, Machine Learning for Signal Processing (MLSP) 2008, pp. 73 – 78.

[80] **A.-H. Phan**, A. Cichocki and K. S. Nguyen: “Simple and efficient algorithm for distributed compressed sensing”, Machine Learning for Signal Processing (MLSP) 2008, pp. 61 – 66.

[81] **A.-H. Phan**, A. Cichocki: “Multi-way nonnegative tensor factorization using fast hierarchical alternating least squares algorithm (HALS)”, In proceeding of the 2008 International Symposium on Nonlinear Theory and its Applications (NOLTA2008), Budapest, Hungary, Sept 7-10.

[82] **A.-H. Phan**, A. Cichocki and K. S. Nguyen: “Novel approach for multidimensional data reconstruction and compression”, In proceeding of the 2008 International Conference on Advanced Technologies for Communications and REV’08, Hanoi.

[83] A. Cichocki, **A.-H. Phan**, R. Zdunek, and L.-Q. Zhang. Flexible component analysis for sparse, smooth, nonnegative coding or representation. In Lecture Notes in Computer Science, LNCS-4984, volume 4984, pages 811–820. Springer, 2008.

[84] **A.-H. Phan **and A. Cichocki. Fast and efficient algorithms for nonnegative Tucker decomposition. In Proc. of The Fifth International Symposium on Neural Networks, Springer LNCS-5264, pages 772–782, Beijing, China, 24–28, September 2008.

[85] **A.-H. Phan**, K.-S. Nguyen, A New Robust Algorithm for ICA Based on α-Renyi Entropy and Minimum Spanning Tree, REV’06 (10th Vietnam Conference on Radio & Electronics), SESSION 4. SIGNAL PROCESSING & CODING, 2006.

[86] **A.-H. Phan**, K.-S. Nguyen, New Quality Measure for ICA: Simple, Effective and Intuitive, REV’06 (10th Vietnam Conference on Radio & Electronics), SESSION 4. SIGNAL PROCESSING & CODING, 2006.

[87] L. A. Nguyen, **A.-H. Phan**, K.-S. Nguyen, A Video Stabilization Proposal Using a Nine-Parameter Affine Model, REV’04 (9th Vietnam Conference on Radio & Electronics), Nov. 27-28, 2004, pp. 286-290.

[88] **A.-H. Phan**, L. A. Nguyen, K.-S. Nguyen, A New Affine Transform Model: 9-Parameter Model, Proceedings of the 2004 International symposium on advanced Science and Engineering, HCM City University of Technology and Pukyong National University (Korea), May, 20-21, 2004, pp. 8-11.

[89] K.-S. Nguyen, **A.-H. Phan**, Th. T. Dang, Gaussian Noise Filtering on Video By Coring Technique and Wavelet Transform, Proceedings of the 8th Conference on Science and Technology, 25-26 April, 2002, pp. 103-108 (VNU-HCM).

[90] K.-S. Nguyen, **A.-H. Phan**, L. A. Nguyen, Digital Video Restoration System (DVRS) for Broadcasting Purpose, REV’02 (8th Vietnam Conference on Radio & Electronics), No. 2-3, 2002, pp. 221-224.

**Toolboxes **

[1] A. Cichocki, S Amari, K Siwek, T Tanaka, **A.H. Phan**, R Zdunek, S Cruces, ICALAB toolboxes, url: http://www. bsp. brain. riken. jp/ICALAB.

[2] **A.-H. Phan**, NFEA toolbox: A toolbox for N-way Feature Extraction and Applications, url: http://www. bsp. brain. riken. jp/~phan/nfea/.

[3] **A.-H. Phan**, P. Tichavsk. , and A. Cichocki, Tensorbox: a tensor toolbox for tensor decompositions, url: http://www. bsp. brain. riken. jp/~phan/, 2013.

**Science Projects **

[1] **A.-H. Phan **(leader and principal researcher) “Data and Application Broadcasting for Digital Television”, 2007 (Excellent evaluation).

[2] **A.-H. Phan **(leader and major researcher) “Vietnamese Electronic Program Guide for Vietnam Television”, Vietnam Television project, Aug 2006. Excellent evaluation.

[3] **A.-H. Phan **(leader and principal researcher) “Data and Application Broadcasting for Digital Television”, 2007 (Excellent evaluation).

[4] K. S. Nguyen (leader), **A.-H. Phan **(principal researcher)…”Blind Sources Separation with The Number of Signal Sources is More Than That of Sensors Using ICA (Independent Component Analysis)”, International University, Vietnam National University-Hochiminh City, 2005, Good evaluation.

[5] **A.-H. Phan **(leader and principal researcher) Nguyen Kim Sach, Dang Thanh Tin … “The system for automatically recognizing and reducing the noise of video”, Vietnam Television project, Jan 2004, Excellent evaluation.

[6] K. S. Nguyen (leader), **Phan Anh Huy **(principal researcher), Dang Thanh Tin … “Designing the system for video restoration and improvement”, Vietnam Television project, July 2001, Good evaluation.

**Workshop, Invited Talk **

[1] S. R. Lehky, **A. -H. Phan**, A. Cichocki, and Keiji Tanaka, Coding of Faces by Tensor Components, The 12th International Neural Coding Workshop, 2016, https://events.uni-koeln.de/frontend/index.php?folder_id=106.

[2] P. Tichavský, **A. -H. Phan**, and A. Cichocki, “Numerical CP decomposition of some difficult tensors”, in TDA workshop, 2016.

[3] **A.-H. Phan**, Tensor decompositions for multiway classification. SIAM workshop, TDA 2010, Bari, Italy.

[4] A. Cichocki, and **A.-H. Phan**, Multi-way array (tensor) factorizations and decompositions and their potential application, ICA 2009, Paraty, Brazil (invited talk).

**A.-H. Phan, Outstanding Reviewer Award** for maintaining the prestige of ICASSP 2019.

Andrzej Cichocki, Danilo P. Mandic, Anh Huy Phan, Cesar F. Caiafa, Guoxu Zhou, Qibin Zhao, and Lieven De Lathauwer, “Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysis” IEEE Signal Processing Magazine, March 2015, the 2018 SPS Signal Processing Magazine **Best Paper Award**

N. Lee, **A.-H. Phan**, F. Cong, A. Cichocki, Nonnegative tensor train decompositions for multi-domain feature extraction and clustering, International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, vol. 9949, pp.87-95, 2016 (**best paper award**).

**A.-H. Phan, RIKEN Research and Technology Incentive Award, 2018 **

- Nov. 2020, our paper “Deep convolutional tensor network” has been accepted to appear in the Quantum Tensor Networks in Machine Learning Workshop at NeurIPS 2020.

– August 2020, our paper “stable low-rank tensor decomposition for compression of convolutional neural network” will be presented in ECCV’ 2020.

– Nov. 13, 2019, our paper “Tensor Networks for Latent Variable Analysis: Novel Algorithms for Tensor Train Approximation” has received final approval for publication in the IEEE Transactions on Neural Networks and Learning Systems.

– Oct. 24, 2019, our paper “Face Representations via Tensorfaces of Various Complexities” will appear in MIT Neural Computation, 2019.

– Sep. 17, 2019, our paper “Sensitivity in tensor decomposition” will appear in IEEE Signal Processing Letters, 2019.

– July 2, 2019, our paper “Tensor Networks for Latent Variable Analysis: Higher Order Canonical Polyadic Decomposition” has received final approval for publication in the IEEE Transactions on Neural Networks and Learning Systems.

– April. 2019, our paper entitled “Quadratic Programming Over Ellipsoids with Applications to Constrained Linear Regression and Tensor Decomposition” has been accepted for publication in Neural Computing and Applications, 2019

– Dec. 2018, our paper “Article Title: Error Preserving Correction: A Method for CP Decomposition at a Target Error Bound” will appear in IEEE Transaction on Signal Processing, 2019.

– Nov. 2018, Our paper published in IEEE Signal Processing Magazine has been selected for the 2018 **SPS Signal Processing Magazine Best Paper Award**.

Andrzej Cichocki, Danilo P. Mandic, Anh Huy Phan, Cesar F. Caiafa, Guoxu Zhou, Qibin Zhao, and Lieven De Lathauwer, “Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysis” IEEE Signal Processing Magazine, March 2015.

– Aug. 2018, A new version of the TENSORBOX (v.2018) is available online in August 2018.

—–

A new version of the TENSORBOX (v.2018) is available online in August 2018.

Tensor Decompositions and Tensor Networks in Artificial Intelligence (2021-2022: Term 1)

Matrix and Tensor Factorizations (2020-2021: Term 5)

Matrix and Tensor Factorizations (2019-2020: Term 3)

Matrix and Tensor Factorizations (2018-2019: Term 4)

Convex Optimization and Applications (2021-2022: Term 2)

Convex Optimization and Applications (2020-2021: Term 2)

Convex Optimization and Applications (2019-2020: Term 2)

Convex Optimization and Applications (2018-2019: Term 2)