Difference between revisions of "Vadim"

Revision as of 21:13, 28 September 2022

Vadim is a Doctor of Sciences in Physics and Mathematics, a professor at the Moscow Institute of Physics and Technology.

Fields of research

AI, Machine Learning and Data Analysis, Deep Learning
Functional and Geometric Learning, Physics-Informed learning
Behavioural Analysis and Brain-Computer Wearable Interfaces

Activities

Makes long-term planning of applied and theoretical research. Leads and runs research projects in the field of AI: states problems, connects researchers and programmers, delivers projects to implementation and publications

%\includegraphics[width=5cm]{str200.jpg} %\end{tabular}

Duties

2004–2022 Doctor of physico-mathematical sciences, Principal investigator at the Computing Center of the Russian Academy of Sciences
2010–2022 Professor, chief of department at the Moscow Institute of Physics and Technology
2019–2022 Chief scientist of the Laboratory of Machine Intelligence at MIPT
2006 Consultant on human behaviour analysis projects at Forecsys Ltd
2015-2022 Chair of the MS thesis committee at the Skolkovo Institute of Science and Technology
2015-2022 Chair of the BS thesis committees at the University Higher School of Economics
2011–2019 Editor in chief of the Journal of Machine Learning and Data Analysis

Teaching courses

Automation Research in Machine Learning – My First Scientific Paper: each year this course delivers over 30 supervised student projects and publications
Signal and Functional Data Analysis – Mathematical Methods of Forecasting
Machine learning and Data analysis}: in 2015 with colleagues obtained a grant from Coursera.org to create a MOOC specialization, eight consequent courses
2018–2022 Plans and runs five courses with his PhD alumni:
- Bayesian Model Selection,
- Generative Deep Learning Models,
- Bayesian Multi-modeling,
- Communications in Machine Learning Research,
- Fundamental Theorems of Machine Learning

Supervision of research activities

Alumni under scientific supervision: 32 BS, 28 MS, 16 PhD students. Now in his team 9 BS, 13 MS, 7 PhD students

PhD thesis, supervised and defended

now the students are working for Amazon, Yahoo, Meta, WorldQuant:

2014 Algebraic graph transformations for non-linear model generation
2015 Concordance of the partial ordered expert estimations
2017 Multi-model selection for classification problem
2017 Hierarchical topic modelling for short-text collections
2019 Multi-way feature selection for ECoG-based Brain-Computer Interface
2020 Bayesian model selection for deep learning neural network structures
2021 Dimensionality reduction for ECoG Brain-Computer Interface time series
2022 Expert learning and Bayesian multi-modelling

Scheduled

2023 Spatial-time series multiple alignment and clustering
2024 Continuous space-time differential models for Brain-Computer Interface

Organisational duties

Responsible for French Institute for Research in Computer Science and Automation INRIA-MIPT collaboration
Examiner of the PhD thesis committee at the Grenoble-Alpes University
Member of PhD thesis committee at the Russian Academy of Sciences, Computing Centre
Chair of the MS/PhD thesis committee at the Skolkovo Institute of Science and Technology
Chair of the BS thesis committees at the National Research University Higher School of Economics
Editor in chief of the Journal of Machine Learning and Data Analysis
Executive chair of the International Conference on Intelligent Data Processing]
Program committee member of the International Federation of Operational Research Societies

Visiting professor

2013 University of Siegen (Germany), delivers a course Data Analysis in Business Analytics
2014 Middle East Technical University (Turkey), delivers a course on Model Selection in Machine learning
2014 RWTH Aachen University (Germany), delivers a course on Preference Learning and Model Selection
2015 University of Grenoble, Computer Science Laboratory (France), participates in research projects, devoted to industrial time series forecasting
2019 National Institute of Automation and Informatics (France), plans and organizes scientific research projects in machine learning for bio-informatics

Education

Obtained D.Sc.(2014) and Ph.D.(2002) in Physics and Mathematics with theses on Mathematical Modelling and Machine Learning from Russian Academy of Sciences, Computing Center

Distinctions

Yandex Segalovich prize award in 2020 for his significant impact in the scientific community development in the CIS-countries. Series of grants from Foundation for Basic Research

Impact projects

The physical activity behaviour analysis': resulted in a set of algorithms for deployment in the wearable devices. Proceeded as a three joint start-up companies, which are successfully developing.
Multiway feature selection for ECoG-based Brain-Computer Interface resulted as a feature selection algorithms and a forecasting model to decode the human upper limb movement using the electrocorticogram
Rail-road time series forecasting for the county rail-roads resulted a set of the hierarchical time series forecasting algorithms to deploy to the freight planning
Creation the system of decision making for The Foundation for Basic Research
The theory of model generation and selection. The project resulted as a joint MS program. Laboratory of Machine Intelligence, MIPT and University Grenoble-Alpes
The theory of expert assessment concordance for decision making. The project was made for WWF and IUCN to rank protected areas, national parks and wilderness areas

Patents

Particle Detector} // European Patent Office, patent 06808733.7-1240 PCT/GB2006060369
Time series generation for railway freight models // Software program register, patent 2016617271
Model of railway freight volumes forecasting // Software program register, patent 2016617272

Skills

Scientific and applied research planing and executing, Experiment planning, Electronic devices developing: programmable microchips and printed circuit boards , Programming VHDL, Matlab, Mathematica, C++, Python, Editorial duties and publishing

Strijov-Vadim

Selected publications

Numerical methods of sufficient sample size estimation for generalised linear models // Lobachevskii Journal of Mathematics, 2022 by Grabovoy A.V., Gadaev T.S., Motrenko A.P., Strijov-Vadim (the last author is Vadim)
Prior distribution selection for a mixture of experts // Computational Mathematics and Mathematical Physics, 2021, 61(7): 1149–1161 by Grabovoy A.V., Strijov-Vadim DOI
Disconnected graph neural network for atom mapping in chemical reactions // Physical Chemistry Chemical Physics, 2020 by Nikitin F., Isayev O., Strijov-Vadim DOI
Quasi-periodic time series clustering for human activity recognition // Lobachevskii Journal of Mathematics, 2020, 41: 333-339 by Grabovoy A.V., Strijov-Vadim DOI
Hierarchical thematic classification of major conference proceedings // CICLing, 2020 by Kuzmin A.A., Aduenko A.A., Strijov-Vadim URL
Comprehensive analysis of gradient-based hyperparameter optimisation algorithms // Annals of Operations Research, 2019: 1-15 by Bakhteev O.Y., Strijov-Vadim DOI
Object selection in credit scoring using covariance matrix of parameters estimations // Annals of Operations Research, 2018, 260(1-2): 3-21 by Aduenko A.A., Motrenko\,A.P., Strijov-Vadim DOI
Deep learning model selection of suboptimal complexity // Automation and Remote Control, 2018, 79(8): 1474–1488 by Bakhteev O.Y., Strijov-Vadim DOI
Quadratic programming optimisation with feature selection for non-linear models // Lobachevskii Journal of Mathematics, 2018, 39(9): 1179-1187 by Isachenko R.V., Strijov-Vadim DOI
Multi-way feature selection for ECoG-based brain-computer interface // Expert Systems with Applications, 2018, 114(30): 402-413 by Motrenko\,A.P., Strijov-Vadim DOI
Time series forecasting using RNNs: an extended attention mechanism to model periods and handle missing values // ICONIP 2017, 2017 by Cinar Y.G., Mirisaee H., Goswami P., Gaussier E., Ait-Bachir A., Strijov-Vadim URL
Comprehensive study of feature selection methods to solve multicollinearity problem according to evaluation criteria // Expert Systems with Applications, 2017, 76: 1-11 by Katrutsa A.M., Strijov-Vadim DOI
Generation of simple structured Information Retrieval functions by genetic algorithm without stagnation // Expert Systems with Applications, 2017, 85: 221-230 Kulunchakov A.S., Strijov-Vadim DOI
Extracting fundamental periods to segment human motion time series // IEEE Journal of Biomedical and Health Informatics, 2016, 20(6): 1466 - 1476 by Motrenko A.P., Strijov-Vadim DOI
Analytic and stochastic methods of structure parameter estimation // Informatica, 2016, 27(3): 607-624 by Kuznetsov M.P., Tokmakova A.A., Strijov-Vadim DOI
Stress-test procedure for feature selection algorithms // Chemometrics and Intelligent Laboratory Systems, 2015, 142: 172-183 by Katrutsa A.M., Strijov-VadimDOI
Ordinal classification using Pareto fronts // Expert Systems with Applications, 2015, 42(14): 5947–5953 by Stenina M.M., Kuznetsov M.P., Strijov-Vadim DOI
Supervised topic classification for modeling a hierarchical conference structure // in S. Arik et al. (Eds.): International conference on neural information processing, Part 1, LNCS, 2015, 9489: 90–97. by Kuznetsov M.P., Clausel M., Amini M.-R., Gaussier\,E., Strijov-Vadim DOI
Editorial of the special issue data analysis and intelligent optimization with applications // Machine Learning, 2015, 101(1-3): 1-4 by Strijov-Vadim, Weber G.W., Weber\,R., Sureyya O.A. DOI
Methods of expert estimations concordance for integral quality estimation // Expert Systems with Applications, 2014, 41(4-2): 1988-1996 by Kuznetsov M.P., Strijov-Vadim DOI
Bayesian sample size estimation for logistic regression // Journal of Computational and Applied Mathematics, 2014, 255: 743-752 by Motrenko A.P., Strijov-Vadim, Weber~G.W. DOI
Evidence optimisation for consequently generated models // Mathematical and Computer Modelling, 2013, 57(1-2): 50-56 by Strijov-Vadim, Krymova E.A., Weber\,G.W. DOI
Integral indicator of ecological impact of the Croatian thermal power plants // Energy, 2011, 36(7): 4144-4149 by Strijov-Vadim, Granic G., Juric J., Jelavic B., Maricic S.A. DOI

@@ Line 99: / Line 99: @@
 Scientific and applied research planing and executing, Experiment planning, Electronic devices developing: programmable microchips and printed circuit boards , Programming VHDL, Matlab, Mathematica, C++, Python, Editorial duties and publishing
+Strijov-Vadim
 ==Selected publications==
+* ''Numerical methods of sufficient sample size estimation for generalised linear models'' // Lobachevskii Journal of Mathematics, 2022 by Grabovoy A.V., Gadaev T.S., Motrenko A.P., Strijov-Vadim (the last author is Vadim)
-<!--
+* ''Prior distribution selection for a mixture of experts'' // Computational Mathematics and Mathematical Physics, 2021, 61(7): 1149–1161 by Grabovoy A.V., Strijov-Vadim [https://doi.org/10.1134/S0965542521070071 DOI]
-==Achievements of impact==
+* ''Disconnected graph neural network for atom mapping in chemical reactions'' // Physical Chemistry Chemical Physics, 2020 by Nikitin F., Isayev O., Strijov-Vadim [https://doi.org/10.1039/D0CP04748A DOI]
-* Plans 600 projects in ML, the most part were successfully implemented
+* ''Quasi-periodic time series clustering for human activity recognition'' // Lobachevskii Journal of Mathematics,  2020, 41: 333-339 by Grabovoy A.V., Strijov-Vadim [https://doi.org/10.1134/S1995080220030075 DOI]
-* Competence to create a number of small research groups, which reach a given goal during limited amount of time
+* ''Hierarchical thematic classification of major conference proceedings'' // CICLing, 2020 by Kuzmin A.A., Aduenko A.A., Strijov-Vadim [http://strijov.com/papers/Kuzmin2017HierarchicalThematic.pdf URL]
-* Used to plan a project “from goal to start, given resources”, not “as it goes”
+* ''Comprehensive analysis of gradient-based hyperparameter optimisation algorithms'' // Annals of Operations Research, 2019: 1-15 by Bakhteev O.Y., Strijov-Vadim [https://doi.org/10.1007/s10479-019-03286-z DOI]
--->
+* ''Object selection in credit scoring using covariance matrix of parameters estimations'' // Annals of Operations Research, 2018, 260(1-2): 3-21 by Aduenko A.A., Motrenko\,A.P., Strijov-Vadim [https://doi.org/10.1007/s10479-017-2417-3 DOI]
+* ''Deep learning model selection of suboptimal complexity'' // Automation and Remote Control, 2018, 79(8): 1474–1488 by Bakhteev O.Y., Strijov-Vadim [https://dx.doi.org/10.1134/S000511791808009X DOI]
+* ''Quadratic programming optimisation with feature selection for non-linear models'' // Lobachevskii Journal of Mathematics, 2018, 39(9): 1179-1187 by Isachenko R.V., Strijov-Vadim [https://doi.org/10.1134/S199508021809010X DOI]
+* ''Multi-way feature selection for ECoG-based brain-computer interface'' // Expert Systems with Applications, 2018, 114(30): 402-413 by Motrenko\,A.P., Strijov-Vadim [https://doi.org/10.1016/j.eswa.2018.06.054 DOI]
+* ''Time series forecasting using RNNs: an extended attention mechanism to model periods and handle missing values'' // ICONIP 2017, 2017 by Cinar Y.G., Mirisaee H., Goswami P., Gaussier E., Ait-Bachir A., Strijov-Vadim [https://arxiv.org/pdf/1703.10089.pdf URL]
+* ''Comprehensive study of feature selection methods to solve multicollinearity problem according to evaluation criteria'' // Expert Systems with Applications, 2017, 76: 1-11 by Katrutsa A.M., Strijov-Vadim [https://doi.org/10.1016/j.eswa.2017.01.048 DOI]
+* ''Generation of simple structured Information Retrieval functions by genetic algorithm without stagnation'' // Expert Systems with Applications, 2017, 85: 221-230 Kulunchakov A.S., Strijov-Vadim [https://doi.org/10.1016/j.eswa.2017.05.019 DOI]
+* ''Extracting fundamental periods to segment human motion time series'' // IEEE Journal of Biomedical and Health Informatics, 2016, 20(6): 1466 - 1476 by Motrenko A.P., Strijov-Vadim [https://doi.org/10.1109/JBHI.2015.2466440 DOI]
+* ''Analytic and stochastic methods of structure parameter estimation'' // Informatica, 2016, 27(3): 607-624 by Kuznetsov M.P., Tokmakova A.A., Strijov-Vadim [https://dx.doi.org/10.15388/Informatica.2016.102 DOI]
+* ''Stress-test procedure for feature selection algorithms'' // Chemometrics and Intelligent Laboratory Systems, 2015, 142: 172-183 by Katrutsa A.M., Strijov-Vadim[https://doi.org/10.1016/j.chemolab.2015.01.018 DOI]
+* ''Ordinal classification using Pareto fronts'' // Expert Systems with Applications, 2015, 42(14): 5947–5953 by Stenina M.M., Kuznetsov M.P., Strijov-Vadim [https://doi.org/10.1016/j.eswa.2015.03.021 DOI]
+* ''Supervised topic classification for modeling a hierarchical conference structure'' // in S. Arik et al. (Eds.): International conference on neural information processing, Part 1, LNCS, 2015, 9489: 90–97. by Kuznetsov M.P., Clausel M., Amini M.-R., Gaussier\,E., Strijov-Vadim [https://doi.org/10.1007/978-3-319-26532-2_11 DOI]
+* ''Editorial of the special issue data analysis and intelligent optimization with applications'' // Machine Learning, 2015, 101(1-3): 1-4 by Strijov-Vadim, Weber G.W., Weber\,R., Sureyya O.A. [https://doi.org/10.1007/s10994-015-5523-y DOI]
+* ''Methods of expert estimations concordance for integral quality estimation'' // Expert Systems with Applications, 2014, 41(4-2): 1988-1996 by Kuznetsov M.P., Strijov-Vadim [https://doi.org/10.1016/j.eswa.2013.08.095 DOI]
+* ''Bayesian sample size estimation for logistic regression'' // Journal of Computational and Applied Mathematics, 2014, 255: 743-752 by Motrenko A.P., Strijov-Vadim, Weber~G.W. [https://doi.org/10.1016/j.cam.2013.06.031 DOI]
+* ''Evidence optimisation for consequently generated models'' // Mathematical and Computer Modelling, 2013, 57(1-2): 50-56 by Strijov-Vadim, Krymova E.A., Weber\,G.W. [https://doi.org/10.1016/j.mcm.2011.02.017 DOI]
+* ''Integral indicator of ecological impact of the Croatian thermal power plants'' // Energy, 2011, 36(7): 4144-4149 by Strijov-Vadim, Granic G., Juric J., Jelavic B., Maricic S.A. [https://doi.org/10.1016/j.energy.2011.04.030 DOI]

Navigation menu