PhD Positions
Currently listed open PhD positions have the following timeframe:
- Application deadline: 1 August 2021 (see application period)
- Start Date: 1 November 2021
- Duration of PhD project: 4 years
Skoltech Center CDISE aims at the conduction of cross-cutting interdisciplinary research driven by modern applications in the fields of computational and data sciences. CDISE has accumulated 20+ research groups all with unique expertise in Russia and competitive at the world level in their prospective areas:
All PhD studentships in Skoltech are by default covered with a generous stipend of 75,000₽ in addition to health coverage for the duration of graduate studies, provided that academic standards are met, and progress towards a PhD degree is maintained. Check for more details in Skoltech policy on student stipends and other benefits.
Uncertainty Estimation in Machine Learning (Prof. Maxim Panov)
| Research Supervisor | Assistant Professor Maxim Panov () |
| Research Group | Statistical Machine Learning | https://sites.skoltech.ru/statml/ |
| Project Description | The objective of this project is to develop methods for estimating the uncertainty of predictions of machine learning algorithms and to develop experiment planning procedures and Bayesian optimization based on them.In many areas of modern science and technology, in particular in industrial design, modeling of chemical compounds and materials, industrial production and economic process control systems, and many others, it is necessary to construct models of the systems under consideration which make it possible to draw conclusions about their properties and predict their behavior. Moreover, it is important to not only create the models but also to estimate uncertainty for them and to optimize these systems.In all the problems described above, the possibility to estimate the uncertainty of the model predictions plays a major role. For the prediction problem, an uncertainty estimate is necessary to detect those points at which the prediction of the model is unreliable. In the problem of detecting anomalies, the estimation of uncertainty is necessary in order to distinguish between the deviations associated with a high dispersion of the prediction and the anomalous deviations of the average value of the forecast. In the problem of optimizing functions, the calculation of which is expensive, the estimation of uncertainty allows balancing between the search for the optimum in the vicinity of the best-known point and a broader study of the search space. Finally, in the task of designing an experiment, points with high forecast uncertainty are good candidates for addition to the training set.Note that not all machine learning models have built-in capabilities for assessing the uncertainty of their forecast. The most popular model with a “built-in” uncertainty estimate is a regression model based on Gaussian processes, in which the posterior dispersion of the Gaussian process acts as an estimate of uncertainty. Currently, there are a large number of optimization procedures, adaptive design of an experiment, detection of anomalies, and others based on this model. However, a significant drawback of this model is its high computational complexity, which limits its applicability to problems with large amounts of data. Also, this model was initially limited by the need to specify a parametric family of covariance functions, the choice of which in practice is complicated since one needs to explicitly take into account the features of the problem being solved.
Predictive models based on modern neural networks have significantly less computational complexity at the training stage, and also make it relatively easy to incorporate into the model various features of the problem being solved (for example, translational invariance in the image recognition problem). However, methods for estimating the uncertainty for neural networks have begun to be actively developed only in recent years and are still at a relatively early stage of development, without giving sufficiently accurate estimates of the prediction uncertainty in many applications. In this project, we plan to develop a methodology for estimating uncertainty for neural networks and apply it to the development of specific active learning and adaptive design of experimental procedures, which in turn will be used to solve a number of important applied problems. This project focuses on solving the following key tasks:
|
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Memristor Technologies for Emerging Computing Systems (Prof. Dmitry Yudin)
| Research Supervisor | Assistant Professor Dmitry Yudin () |
| Research Group | Cognitive Computing Hardware https://faculty.skoltech.ru/people/dmitryyudin |
| Project Description | Nowadays, neuromorphic computing is considered one of the most promising approaches for resolving the critical problems that conventional CMOS (complementary metal-oxide-semiconductor) technology faces upon continual miniaturization and ever-increasing power consumption. Owing to the low-power performance and brain-inspired massively parallel computing principles, a large number of bio-inspired algorithms and devices have been attempted in complex pattern recognition, image processing, and data mining. Intensive research has been conducted towards developing learning-based artificial synapses and neurons, attempting to reproduce the behavior of these two fundamental building blocks in biological neural networks. Memristor, a passive component capable of changing its resistance depending on the electric charge passing through, has been proposed as a suitable artificial synapse and neuron for emerging computing systems.In this project, we aim at adapting single-crystalline silicon memristors with alloying conducting channels for neuromorphic realizations of on-chip deep learning. We investigate how these memristors may be tailored to provide novel concept devices to secure stable and controllable device operation, thus enabling large-scale implementation of neuromorphic computing. We will propose machine learning algorithms suitable for this particular platform and evaluate their performance, including data storage, parallel updating of weights, and matrix multiplication. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Digital Metasurfaces for Wireless Terahertz Communications (Prof. Dmitry Yudin)
| Research Supervisor | Assistant Professor Dmitry Yudin () |
| Research Group | Cognitive Computing Hardware https://faculty.skoltech.ru/people/dmitryyudin |
| Project Description | Fifth-generation (5G) mobile communications rapidly deployed nowadays all around the world are expected to bring reduced latency, enhanced energy-efficiency, and higher data rate. In practice, with a peak speed of about 10 Gb/s and a channel bandwidth of 0.1-1 GHz making use of mm-wave carriers becomes unavoidable. However, 5G will hardly be an adequate solution in the short run owing to growing demands and needs for machine connectivity, e.g., the Internet of Things (IoT). The emerging sixth-generation (6G) is still in its germinal phase with no clear definition behind it: it is however clear that switching to terahertz frequency electromagnetic waves (0.1-10 THz) is an essential prerequisite. Metasurfaces, representing an array of artificial unit cells each of which is characterized by its own electromagnetic response, provide us with a unique tool for wave manipulations, particularly in the terahertz spectrum.In this project, we explore index modulation, which is considered as one of the possible solutions towards next-generation wireless communications, in a multiple-input multiple-output (MIMO) array using programmable metasurfaces. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Machine Learning-based Stochastic Trajectories Characterization and Inpainting (Prof. Vladimir Palyulin)
| Research Supervisor | Assistant Professor Vladimir Palyulin () |
| Research Group | Vladimir Palyulin |
| Project Description | Random processes produce random trajectories. In order to understand the nature of stochastic phenomena behind a wide range of phenomena from motions of proteins in a living cell to human behavioral strategies, one has to infer a model from the trajectory information. Recent advances in machine learning offer an opportunity to create tools for trajectory characterization. These tools can be noticeably more efficient than the conventionally used mean-squared displacement approach.The project consists of the development of new ML-based frameworks for trajectory characterization, segmentation, and inpainting. The latter problem appears when only the parts of the trajectory are known from the measurements. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Towards Real-time-capable Reinforcement Learning with Integrated Safety (Prof. Pavel Osinenko)
| Research Supervisor | Assistant Professor Pavel Osinenko () |
| Research Group | Artificial Intelligence in Dynamic Action | https://sites.skoltech.ru/aida |
| Project Description | When machine learning comes into the world of dynamic environments, it faces a qualitatively new set of challenges. Think of a task of face generation like in StyleGAN, or photo enhancement – these tasks are performed in an inherently safe environment: there is nothing that threatens anyone during the learning phase.Reinforcement learning, which is considered by some as the vanguard of ML, is supposed to imitate the behavior of living beings by an adaptation to the environment via trial-and-error. Living beings, however, do not blindly try out actions — they reason, although, depending on species, maybe in a somewhat primitive way. In most reinforcement learning applications, we rather deal with more or less safe environments where we can first train the neural nets, e.g., actor, critic. model estimator, with sufficient data, and then run them on-field. The cost of a failure during the learning phase is relatively low in such scenarios. Consider AlphaZero, the famous chess bot, based on reinforcement learning. Evidently, a loss in a blitz game is just yet another entry in the data set. Open AI Gym, a popular Python tool of reinforcement learning, learns the agents by trial-and-error also.  But what should one do when dealing with real-world applications where no luxury of multiple trials and errors is available? Aircraft, autonomous cars, industrial equipment, robots – there are tons of cases where “playground” conditions are not provided. On the contrary, one faces strict requirements on safety and operational regulations. Traditionally, all of these have been addressed by control and system theory with its long-established machinery of model-based policies with built-in safety constraints.The challenge of this project is to develop a reinforcement learning approach free of the necessity of a long training phase and capable of more or less “hot start” like traditional control. Here is a question to think about: can we develop a hybrid of reinforcement learning and model-based, predictive engines to possess the intelligence of machine learning and strict guarantees like traditional control? For the time being, reinforcement learning is barely applicable in industry precisely due to the limitations described. If we want to roll out a really commercializable algorithm – we need to address the above challenge.
We may take the general reinforcement learning setup and investigate how it can be augmented so as to become fully online-capable. There are several ways of tackling this. A particular one is to build reinforcement learning on top of some nominal controller that guarantees safety by default and launch the learning in a virtual environment where such a controller is ambient. Another way is to balance data-driven elements of reinforcement learning with predictive controls. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Predictive Reinforcement Learning with Applications (Prof. Pavel Osinenko)
| Research Supervisor | Assistant Professor Pavel Osinenko () |
| Research Group | Artificial Intelligence in Dynamic Action | https://sites.skoltech.ru/aida |
| Project Description | Further development of reinforcement learning (RL) and its recognition in the human economy requires the integration of intelligent machinery capable of functioning beyond plain trial-and-error. A recent and promising variant of such machinery is predictive controls. For instance, there are approaches that successfully combine model-predictive control (MPC) with RL. This project is devoted to studies of prediction-based augmentations of RL, in particular, model-free, e.g., via online model learning. Such a methodology may be seen as a sort of reminiscent of Google’s RL dreamer.  This project addresses not only theoretical aspects of predictive RL but seeks to apply it in applications, in particular:
An application may be chosen from the above list or, alternatively, picked upon agreement between the candidate and the supervisor. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Knowledge Base Question Answering (Prof. Alexander Panchenko)
| Research Supervisor | Assistant Professor Alexander Panchenko () |
| Research Group | Natural Language Processing | https://sites.skoltech.ru/nlp |
| Project Description | Knowledge Base Question Answering (KBQA) is a technology that can be used to enrich the experience of search engine users by directly providing an answer to their questions. However, according to recent studies, state-of-the-art systems for the Russian language yield performance on this task ranging from 12% to 32% of precison@1 score, depending on the dataset and settings. Such low absolute scores hinder an industrial application of the KBQA technologies, e.g. in the form of integration into a search engine.This project aims at researching and developing a technology for a knowledge base question answering system for the Russian language that will try to overcome this limitation by improving the current results for the Russian language in terms of absolute numbers; developing techniques for selection of highly reliable answers – to favor high precision – with a possibly lower recall. Besides, the project is going to explore how to transfer the developed technology to languages other than Russian. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Automatic refinement of dialogue systems output (Prof. Alexander Panchenko)
| Research Supervisor | Assistant Professor Alexander Panchenko () |
| Research Group | Natural Language Processing | https://sites.skoltech.ru/nlp |
| Project Description | The output of a neural generation model, such as RNN or Transformer, is difficult to control. This happens because such models are trained on large volumes of text data which usually come from the web. Such texts exist in large amounts and are constantly renewed, using them allows training models on up-to-date topics and vocabulary. However, such an abundance of texts cannot be checked for quality. User-generated content can include obscene lexis, toxicity, and other undesirable elements that are difficult to detect automatically.As a result, a model trained on data from the web can potentially generate an undesirable text. Since the preemptive check of text appropriateness is impossible, using neural models in commercial applications is too risky. This often makes developers of generation models resort to less flexible, but more reliable and controllable models, such as rule-based dialogue systems based on scenarios.The goal of this work is to increase the reliability of neural dialogue models by creating an external automatic censor that will evaluate a generated utterance and decide if it is acceptable for a dialogue. The censor will consist of two components: a model that evaluates the quality of generated text and a model that re-formulates the unacceptable text. The Quality evaluation model will define if a text contains inappropriate elements, namely obscene phrases, offense, too informal phrases, undesirable topics. It will also need to model the dialogue flow because a neutral phrase can become offensive in some contexts. The re-formulation model should re-write an unacceptable utterance in such a way that it keeps its content but the tone becomes acceptable.
There currently exist no systems that could identify and correct unacceptable utterances on the fly. The existing automatic censors for chatbots usually rely on lists of potentially dangerous keywords. This approach can overlook offenses that do not contain obscene words. We would like to create a model that considers features of a higher level. Moreover, existing models do not suggest inoffensive alternatives for the discovered offensive messages. While text paraphrasing and style transfer of texts is an active topic of research, the task of transforming toxic text to neutral has only been considered in a few research works. Thus, the work will include collecting new datasets and devising new methods that take into account the specificity of the task. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Depth SLAM enhanced by Machine Learning (Prof. Gonzalo Ferrer)
| Research Supervisor | Assistant Professor Gonzalo Ferrer () |
| Research Group | Mobile Robotics | https://sites.skoltech.ru/mobilerobotics |
| Project Description | SLAM is an active and open research problem for the robotics and computer vision communities. In this project, we propose the study of geometric information obtained from depth sensors such as 2D LIDARs, 3D LIDARs, ToF or RGBDs to be used in SLAM, both in the front end by extracting features and in the back end for more efficient calculations [1]. In this process of obtaining features, we propose to exploit geometric features, such as planes [2] or other regular surfaces, and the use of machine learning to provide new alternatives.[1] https://github.com/MobileRoboticsSkoltech/mrob[2] Ferrer, G. “Eigen-Factors: Plane Estimation for Multi-Frame and Time-Continuous Point Cloud Alignment.” IROS. 2019. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Social Robot Navigation using Learning Techniques (Prof. Gonzalo Ferrer)
| Research Supervisor | Assistant Professor Gonzalo Ferrer () |
| Research Group | Mobile Robotics | https://sites.skoltech.ru/mobilerobotics |
| Project Description | For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to correctly understand and model subtle human behaviors and common navigation rules. In the past, Model-based prediction algorithms have delivered satisfactory results [1,2]. However, once the number of interactions and complexity of the environment increase, one should seek alternative solutions that correctly handle these challenges, such as richer expressivity of paths generated, evaluation of risk [3], or simply explainability of the decision making. Recently, tremendous advances have been shown in learning techniques in multiple fields. In the robotics discipline, especially on robot navigation, there have been several research works pioneering the idea of using Gaussian Process, Deep Reinforcement Learning, or Generative Adversarial Networks, to name a few. Unfortunately, the improvement over classical techniques is not so spectacular as in other disciplines after using deep learning architectures.The objective of the present project is to further push on the results obtained on human motion prediction and robot navigation algorithms.[1] G. Ferrer, A. Garrell and A. Sanfeliu. Robot Companion: A Social-Force Based Approach with Human Awareness-Navigation in Crowded Environments. IROS, 2013. [2] G. Ferrer and A. Sanfeliu. Anticipative Kinodynamic Planning: Multi-objective Robot Navigation in Urban and Dynamic Environments. Autonomous Robots 2019 [3] D. Mehta, G. Ferrer, and E. Olson. Backprop-MPDM: Faster risk-aware policy evaluation through efficient gradient optimization. ICRA 2018. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Machine Learning in Deorphanization of Potential Drug Targets (Prof. Natalia Strushkevich)
| Research Supervisor | Assistant Professor Natalia Strushkevich () |
| Research Group | Natalia Strushkevich |
| Project Description | Mycobacterium tuberculosis (Mtb) is among the top 10 causes of death worldwide, and the number of drug-resistant species is increasing. The major challenge for anti-tuberculosis drug discovery is the lack of knowledge about the function of many mycobacterial proteins [PMID: 9634230]. Among them are enzymes of the cytochrome P450 (CYP) family, 75% of which do not have an assigned function. Various experimental approaches are used to deorphanize this class of proteins [PMID: 20493973], however, most of them have limitations and cannot be applied to the enzymes that utilize undiscovered molecules. Significant amounts of information accumulated over years of study of human and pathogenic proteins in transcriptomic, metabolomics, structural biology, and other fields could be used for machine learning to predict the protein function.The goal of the project is the application of machine learning to deduce consistent patterns that define the function of unknown CYPs. Predictive algorithms and/or models will be developed with further docking of predicted or de novo designed compounds into the active site of CYPs with known 3D structures. Experimental validation of results is planned within collaborations with different labs. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Computer Modeling of the Protein-Protein Interaction Inhibitors (Prof. Natalia Strushkevich)
| Research Supervisor | Assistant Professor Natalia Strushkevich () |
| Research Group | Natalia Strushkevich |
| Project Description | Protein–protein interaction (PPI) inhibitors are a rapidly expanding class of therapeutics. Many essential cellular functions rely on the precise and timely interaction of proteins forming stable or transient complexes. Recent advances in the design of chemical libraries and the development of HTS methodologies suitable for studying PPIs make them feasible drug targets. Computational approaches have been designed to predict and characterize PPI’s at different levels [PMID: 25330973, PMID: 26231283, PMID: 30020406], however, they are specific for each protein family.In this project, assessing ‘druggability’ (pockets, well-defined grooves, etc.) of proteins forming specific electron transfer complexes will be evaluated based on crystal structures of individual proteins. After molecular docking based on crystal structures of related protein complexes, the “hot” spots or critical residues that anchor two proteins together have to be identified using publically available structural and biochemical data.The final goal is to find either a small molecule or peptide from publically available library collections, which will specifically fit into the protein interaction interface. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Omics Mass Spectrometry-Based Technologies for Improving Personalized Medicine and Health (Prof. Christoph Borchers)
| Research Supervisor | Visiting Professor Christoph Hermann Borchers () |
| Research Group | Laboratory of Omics Technology and Big Data for Personalized Medicine and Health | Christoph Hermann Borchers |
| Project Description | The Laboratory for Omics Technologies and Big Data for Personalized Medicine and Health is looking for PhD students who will be part of the recently awarded Megagrant to Dr. Borchers.The R&D of the laboratory is focused on absolute quantitation of the protein expression, modification status, and mutation rate in biological and clinical samples. One emphasis of the laboratory is on the development and implementation of the “Next Generation Proteomics”, making the protein analysis more sensitive, multiplex, and faster allowing for more applicable and comprehensive analysis of highly complex systems like the proteome of tumors and blood plasma proteome. The students will be educated and trained to use state-of-the-art laboratory equipment, analytical instruments like modern mass spectrometers, and computational software including deep learning and AI.The students will work on technology development projects directly applied to answer biological and medical questions. The students have the opportunity to visit and further enhance their studies at the proteomics laboratory of Dr. Borchers at the McGill University in Montreal, Canada. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Development of Machine Learning Methods for Identification of Pathologies based on the Results of Multimodal Molecular Analysis of Dry Blood Spots (Prof. Evgeny Nikolaev)
| Research Supervisor | Professor Evgeny Nikolaev () |
| Research Group | Mass Spectrometry Laboratory | https://www.skoltech.ru/massspeclab/ |
| Project Description | Analysis of dry blood spots by mass spectrometric methods is the gold standard in neonatal screening for the identification of genetic diseases after the child’s birth. For performing such analysis, the composition of metabolites is determined in the extracts from dry blood spots obtained from the child’s finger or heel. The samples can be delivered to the analytical laboratory by post. Recently, this method has attracted attention as a promising method for detecting socially significant diseases during the remote screening of the population.More than 500 different human proteins and several hundred metabolites and lipids are found and identified in the blood spot extracts. The goal of the project is to develop a method for the diagnosis of various diseases based on the results of the analysis of dry blood spots’ molecular composition. For this purpose, it is planned to accumulate a database of the mass spectra of extraction products from blood spots, which can then be used as a training set for a neural network for the recognition of diseases based on the analysis results.The laboratory has all the necessary equipment to solve this problem, and there is also established cooperation with medical centers of the corresponding profile. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
| Additional comments | Successful students have the opportunity for academic mobility and collaboration with our national and international partners in the UK, Germany, Netherland, France, China, and the USA. |
Development of Machine Learning Methods for Identification of Cancerous Tissues based on Histology, Immunohistochemistry, and Imaging Mass Spectrometry Data (Prof. Evgeny Nikolaev)
| Research Supervisor | Professor Evgeny Nikolaev () |
| Research Group | Mass Spectrometry Laboratory | https://www.skoltech.ru/massspeclab/ |
| Project Description | The main methods for the identification of cancerous tumors are currently histology and immunohistochemistry. In these methods, thin tissue sections are stained with various dyes directly or with antibodies containing chemically stained groups to detect neoplasms in tissues.These procedures are laborious, the range of dyes and antibodies is limited, and a highly qualified, well-trained histologist is required to identify the morphological tissue structures corresponding to various tumors.Modern mass spectrometry makes it possible to “see pathologies” by analyses of the spatial distribution of the corresponding molecular structures directly by point extraction or ablation of molecules from tissue sections. These molecules are ionized and their mass spectra are measured. Peak intensities in the mass spectrum from different molecules along tissue are mapped. Such an approach allows obtaining distribution maps of tumor molecular biomarkers and the morphology of tissues affected by tumors, which can serve as a basis for an objective diagnosis of a tumor. Deep machine learning allows us to develop powerful predictive and objective cancer diagnostic tools. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
| Additional comments | Successful students have the opportunity for academic mobility and collaboration with our national and international partners in the UK, Germany, Netherland, France, China, and the USA. |
Small Molecule Property Prediction using Molecular Modeling & Deep Learning (Prof. Petr Popov)
| Research Supervisor | Assistant Professor Petr Popov () |
| Research Group | iMolecule | https://sites.skoltech.ru/imolecule/ |
| Project Description | The size of chemical space is enormously large counting ~10^60 small molecules. There is a great need for computational tools for the exploration of the chemical space, as it is crucial in drug discovery, material design, molecular design, and other scientific and industrial applications. Deep learning along with molecular modeling techniques allows to development of powerful predictive models to assess physicochemical properties of small molecules to replace expensive and resource-consuming experimental testing.This project aims to apply chemoinformatics, molecular modeling, and deep learning to push the predictive power of quantitative-structure-property-relationship models further. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Computational Design of Proteins with Target Properties Using Molecular Modelling & Deep Learning (Prof. Petr Popov)
| Research Supervisor | Assistant Professor Petr Popov () |
| Research Group | iMolecule | https://sites.skoltech.ru/imolecule/ |
| Project Description | Proteins are working horses of our body. There are ~20K different types of proteins in our body, but this is nothing compared to the possible number of proteins (~20^N, where N is the protein length). Protein sequences are closely related to protein structures and, hence, to protein functions. The design or discovery of proteins with novel properties is a challenging problem in modern science. With progress in deep learning and biotechnology, it is now possible to derive powerful models for protein structure and property prediction, as well as for protein design.This project aims to develop new computational tools to address open problems in protein design. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Computational Prediction of Point Mutation Effects using Molecular Modeling & Deep Learning (Prof. Petr Popov)
| Research Supervisor | Assistant Professor Petr Popov () |
| Research Group | iMolecule | https://sites.skoltech.ru/imolecule/ |
| Project Description | Single amino acid variants, also known as point mutation, in proteins may dramatically change protein’s function leading to disease. On the other hand, engineering point mutations could be useful in biotechnology, for example, to improve the thermostability of the target protein. With the progress in genome sequencing, there is a growing number of experimentally characterized point mutations allowing the use of machine learning approaches to predict the effect of point mutations.This project aims to develop new computational tools to address open problems in the prediction of point mutation’s effects on thermostability and pathogenicity. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Investigation of Neurological Diseases Through Video, Wearables and Machine Learning (Prof. Andrey Somov)
| Research Supervisor | Assistant Professor Andrey Somov () |
| Research Group | Wireless Sensing | http://sites.skoltech.ru/wsensing |
| Project Description | Our society exhibits a worldwide trait of a quickly growing cohort of patients with neurodegenerative diseases such as Parkinson’s Disease (PD). According to the analysts, there is a plausible ‘PD Pandemic’ to occur within the next two decades.In this project, we carry out research on the full framework on the PD/dystonia detection/classification and investigation. In particular, in collaboration with the neurologists, we identify exercises that are typically used to detect the signs of these diseases, design the experimental methodology and experimental testbed. We perform the data collection in real settings with the subjects and data analysis to figure out which exercises guarantee the most accurate disease detection, to learn classifying the stages of the disease, and to understand how to improve the therapy. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
| Additional comments | More details are available upon request. |
Assessment of Physical and Mental Conditions of eSports Players Through Sensing Technologies and Machine Learning (Prof. Andrey Somov)
| Research Supervisor | Assistant Professor Andrey Somov () |
| Research Group | Wireless Sensing | http://sites.skoltech.ru/wsensing |
| Project Description | Competitive video gaming, or eSports, has gained tremendous popularity within the last several years. eSports has evolved into a mature industry with well-funded tournaments, professional athletes, and a vast fan community. The strengthened competition requires professional eSports teams to explore new methods for training and analytics. In its turn, it drives the demand for eSports research.In this project, we deal with multimodal data collection (physiological, environmental, biometric, video, replays) and consequent data analysis using machine learning methods. The project goal is to figure out how the physical conditions influence the psycho-emotional conditions of the player and his team, and how one can improve player/team game performance. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
| Additional comments | More details are available upon request. |
Embedded Deep Learning for Precision Agriculture (Prof. Andrey Somov)
| Research Supervisor | Assistant Professor Andrey Somov () |
| Research Group | Wireless Sensing | http://sites.skoltech.ru/wsensing |
| Project Description | The project goal will be the development of a generic mobile/embedded artificial intelligence system for large-scale detection and monitoring of plants in real time. Direct monitoring of invasive harmful plants using computer vision methods is going to be a unique study that will use the latest achievements in the field of artificial intelligence.The proposed solution will make it possible to react quickly to the hotspot distribution areas of harmful plants and to cover more areas for detection of the plant as well, thus preventing the further rapid spread of these weeds. The use of “mobile” high-performance computing systems for the operation of detecting algorithms will make it possible to develop large-scale applications based on this research. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
| Additional comments | More details are available upon request. |
High-Performance Computing in Extreme Laser Physics (Prof. Sergey Rykovanov)
| Research Supervisor | Associate Professor Sergey Rykovanov () |
| Research Group | High-Performance Computing Research and Education |
| Project Description | High-Performance Computing became a necessity in modern science due to the highly nonlinear nature of the most interesting phenomena in chemistry, engineering, materials science, physics, and astrophysics. Nobel Prize in Physics in 2018 was given for the development of extremely powerful and short laser pulses. Such pulses ionize materials almost instantly and cause extreme, nonlinear, relativistic phenomena similar to that in Space. There are several important areas of extreme laser physics:
Of course, all these areas are impossible to study without the usage of powerful supercomputers. There are several PhD positions within this project depending on the interest and skills of the applicant.
Students, of course, will have the opportunity to interact with the research group and tackle parts of different projects. Projects will be conducted on one of the most powerful supercomputers in Russia “Zhores” boasting 1 petaFLOPS theoretical performance in the GPU partition. Successful students have the opportunity for academic mobility and collaboration with our national and international partners in the UK, Germany, China, and the USA. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
Deep Learning in Scientific Simulations on Supercomputers (Prof. Sergey Rykovanov)
| Research Supervisor | Associate Professor Sergey Rykovanov () |
| Research Group | High-Performance Computing Research and Education |
| Project Description | Scientific Simulations of complex systems (plasmas, atmosphere, pedestrian flows, molecules, etc) are often extremely expensive in terms of computational time prohibiting large parameter scans. On the other hand, the training of Deep Learning networks typically requires a large dataset to succeed.The goal of this project is to apply and improve the recently proposed DENSE method that allows using deep neural networks even with small datasets. The successful candidate will apply this method to various simulations of complex systems such as (but not limited to) complex fluids, plasmas, nonlinear nanophotonics systems, fluid flows in micro- and porous structures.This is an extremely interesting, challenging, and promising project uniting traditional mathematical modeling and AI methods. |
| Eligibility criteria | Candidates should hold or expect an MSc (or an equivalent) degree in the following or closely related disciplines:
Other eligibility criteria:
|
For more details, please get acquainted with the CDSE PhD program details and PhD admission procedure.