Research

CDISE research activities are distributed among the following research groups:

  • Advanced Data Analytics in Science and Engineering (ADASE) (Prof. Evgeny Burnaev)
    ADASE group research is about developing efficient machine learning methods and their use for the solution of applied engineering problems and industrial analytics. In particular, we are working on regression based on Gaussian processes and kernel methods for multi-fidelity surrogate modeling and optimization, Deep Learning for 3D Data Analysis and manifold learning, on-line sequence learning for prediction and non-parametric anomaly detection.
  • Advanced Multiscale Modeling Laboratory (Prof. Nikolay Brilliantov, Prof. Alexey Vishnyakov, Prof. Vladimir Palyulin)
    The main goal of the lab is developing a novel multiscale modeling paradigm, where the emerging methods of Artificial Intelligence (AI) are incorporated into traditional mathematical modeling techniques, such as finite elements, Molecular Dynamics, Langevin Dynamics, Monte Carlo, and Lattice Boltzmann simulations. We explore Complex Systems, such as multiphase Soft Matter (liquids, solutions, complex liquids, porous media, etc.) and Active Matter (self-driven particles, bacteria, animals, pedestrians, vehicles, robotic swarms, drones, etc.). Our primary focus is fundamental academic research that possesses a significant application potential and demand from industry and society.
  • AeroNet Lab (Dr. Vladimir Ignatiev)
    The research of the lab is devoted to the creation of an open benchmark for remote sensing data and their products – a set of images with the labels of different classes, obtained from various aircraft, in particular, satellite imagery, UAV and MA survey. Our lab activities are  to build adaptation procedures of modern intelligent algorithms for data analysis, and also to develop fundamentally new approaches to the processing of multidimensional/multi-fidelity remote sensing data (semantic segmentation, classification, detection of changes, consolidation of heterogeneous data, etc.)
  • Applied Information Theory Group (Prof. Alexey Frolov)
    The group researches the border of information theory, communications, and machine learning with a particular focus on the application of the research results in communications, including engineering and industry problems.
  • Computational Imaging (Prof. Dmitry Dylov)
    The Computational Imaging group, led by Prof. Dylov, has a twofold focus: fundamental mathematical aspects of image formation and applied aspects of image processing and analytics. The synergy between imaging systems and image interpretation is at the forefront of our scientific interest. The team members rely extensively on modern computer vision and deep learning methods, with frequent forays into adjacent disciplines for motivation and new ideas. Historically, our most impactful discoveries belong to the area of biomedical imaging, with applications in optical microscopy, MRI, X-ray/CT scanners, and others. We have built two laboratories at Skoltech, where students can embed their computational algorithms into the consumer cameras and wearable sensors. The main industrial partner of the group is Philips Labs Rus, located in Technopark, where several students are involved in R&D on a joint educational track.
  • Computational Molecular Science (Prof. Maxim Fedorov)
    The primary research interest of the group is in finding new ways in chemical informatics that are based on a combination of physical chemistry methods with machine learning techniques for the prediction of properties of organic compounds. Our primary goal is to develop methods that, on the one hand, are accurate and, on the other hand, are universal and have vast applicability domains.
  • Computer Vision (Prof. Victor Lempitsky)
    Computer vision group research is about designing computer systems that can extract, organize, and quantify information contained in images of various types and origins. For this purpose, the group develops new machine learning techniques (deep learning in particular) and optimization techniques that are robust and flexible enough to handle and to adapt to the diversity of image data in the modern world.
  • Deep Quantum Labs (Prof. Jacob Biamonte)
    We work to understand collective quantum effects, and this understanding enables us to utilize these same collective quantum effects, e.g., in quantum-enhanced machine learning software. Very generally, we call our topic, quantum complexity science. Our approach forms a coherent, challenging, and multidisciplinary research agenda, segmented as four interwoven initiatives: Quantum enhanced software, Quantum complexity science, Tensor networks, Hamiltonian complexity.
  • Digital Agriculture (Prof. Ivan Oseledets and Prof. Maria Pukalchik)
    Our research group is focused on developing efficient machine learning and AI methods to the broad scope of the environment and agriculture issues. Key directions of our team are:
    – predictive analytics for soil fertility and crop yields and 3D soil reconstruction (“digital field”).
    – monitoring, automation, and optimization of greenhouse crop production.
    We have uniques laboratory facilities in collaboration with Dokuchaev soil institute and several climatic chambers and growboxes with different sizes. We also have a fully autonomous mobile chemical laboratory (based on KAMAZ truck). We welcome students and young researchers in the fields of machine learning, computer vision, artificial intelligence, robotics, IoT, and bioinformatics.
  • High-Performance Computing (HPC) (Prof. Sergey Rykovanov)
    Interdisciplinary research topics of our group range from distributed deep learning to mathematical modeling of complex phenomena using modern supercomputers. Using the CDISE flagship supercomputer “Zhores“, we solve challenging computational projects in fluid dynamics, plasma physics, photonics, and other areas using the hybrid approach: traditional parallel numerical modeling coupled with methods of machine learning. Additional research is devoted to evaluating modern high-performance computing (HPC) energy-efficient computing architectures.
  • iMolecule (Prof. Petr Popov)
    iMolecule is an interdisciplinary research group committed to unlocking the full potential of artificial intelligence and machine learning for advanced molecular design. The research area lies at the intersection of molecular modeling, machine learning, and high-performance computing.
  • Internet of Things (IoT) Lab (Prof. Dmitry Lakontsev)
    The research area of IoT Lab is focused on the creation of the IoT products and services for the digital transformation of industrial companies as well as the development of IoT-related solutions for the oil and gas sector, iron and steel industry, aviation, agriculture, etc. In particular, we are currently equipped with testbeds for data collection, processing, and analysis from various enterprise data sources and elaborating the IoT platform suitable for further recommender systems deployment, predictive maintenance, and early production quality control.
  • Laboratory of Applied Research Skoltech-Sberbank (LARSS) (Dr. Alexey Zaytsev)
    LARSS works on the application of digital technologies in the industry and the development of Machine Learning algorithms. In particular, we work in the fields of anomaly detection, kernel methods, embeddings, and Bayesian optimization. We hope that the development of principled methods in Machine learning will push forward both solutions in both theoretical and practical branches of data processing.
  • Laboratory “Tensor networks and deep learning for application in data mining” (Prof. Andrzej Cichocki)
    The Laboratory develops new fundamental approaches for training, testing, and storing parameters of deep neural networks based on tensor decomposition techniques. These approaches allow us to reduce by orders of magnitude computational complexity and required memory for the operation of the network while maintaining a high quality of prediction. The Laboratory mission is to pursue cutting-edge research in the design and analysis of deep neural networks, tensor decompositions, tensor networks, and multiway analysis with many potential practical applications.
    The Laboratory brings together several professors and young researchers in the fields of machine learning, computer vision, artificial intelligence, robotics, large-scale data analysis, mathematics as well as computational neuroscience, and bioinformatics.
  • Machine Learning and Algorithms in Bioinformatics (Prof. Dmitry Yarotsky)
    We are interested in applications of machine learning to bioinformatics and developing efficient algorithms for bioinformatics. Examples of our topics: genotype-to-phenotype prediction, genome reconstruction from contaminated data, optimization of phylogenetic trees.
  • Mass Spectrometry Lab (Prof. Evgeny Nikolaev, Prof. Yury Kostyukevich)
    The Laboratory focuses on the instrumentation development and application of state of the art mass spectrometry techniques. All projects are closely related to modeling of ion behavior in the electromagnetic field as well as the application of different algorithms of the Big data treatment as well as prediction of chemical properties by chemoinformatics approaches. Our primary goal is to develop mass spectrometry platforms and analytical solutions for a wide area of researches.
  • Mobile Robotics Lab (Prof. Gonzalo Ferrer)
    The Mobile Robotics laboratory Bis focused on robot navigation, and mainly our interests are within Path Planning and Perception and how to combine both into new solutions for robotics. The full autonomy milestone for robots has not arrived yet, and we are slowly closing the gap; however, there are still many hindrances, such as uncertainty, scalability, and reliability.
  • Multidimensional Inverse and Ill-posed Problems (MIIP) (Prof. Nikolay Koshev)
    The group focuses on inverse and ill-posed problems of mathematical physics and their applications in various fields of science and industry. Problems of this kind require research on modern methods of solution of integral and partial differential equations, regularization techniques, and high-performance computing. We develop new algorithms and computational software for practical applications in medical physics (electro- and magnetoencephalography, tomography, etc.), geophysics (controlled-source electromagnetics and full-waveform inversion), various kinds of microscopy and tomography (such as electron microscopy and tomography in backscattered electrons), image and signal reconstruction. The group is also involved in the research on the application of deep learning techniques to ill-posed problems.
  • Natural Language Processing (Prof. Alexander Panchenko)
    The goal of the group is research and developments on all aspects of technologies for the processing of natural language. In particular, we are focused on the methods for computational semantics and argument mining and retrieval.
  • Scientific Computing (Prof. Ivan Oseledets)
    Our research focuses on developing breakthrough numerical techniques for solving a broad range of high-dimensional problems. The key ingredient is the effective decomposition of multidimensional arrays (tensors). Our recent interests also involve graph mining, recommender systems, and topological shape optimization.
  • Statistical Machine Learning (Prof. Maxim Panov)
    StatML lab focuses on research in modern statistics and machine learning with particular emphasis on probabilistically inspired approaches. We care about uncertainty a lot and try to ensure that the algorithms developed not only predict the outcome but also provide error bars for the predictions. The current research areas include uncertainty estimation for deep learning, active learning, and network analysis among several others.
  • Structural Learning Group (Prof. Vladimir Spokoiny)
    The research group brings together a group of like-minded researchers and students working in probability, statistics, and optimization. The use of statistical methods for analyzing data has become common practice in virtually all scientific disciplines. We deal with many branches of modern statistics and optimization, including community detection in networks, high-dimensional probability techniques in data analysis.
  • Wireless Sensing (Prof. Andrey Somov)
    Wireless Sensing Lab research focuses on the design, optimization, and implementation of intelligent energy-efficient wireless sensors. We research the low-power wireless sensors running the artificial intelligence onboard and powered by energy harvesting.