Dr Roman Belavkin

Associate Professor in Informatics

Roman Belavkin

  • School Faculty of Science and Technology

  • Department Computer Science

  • Location London

Research activities

  • Value of information theory
  • Dynamics of optimal learning and value of information
  • Optimal parameter control and metaheuristics
  • Evolutionary dynamics
  • Asymmetric spaces and topologies of information
  • Optimal transport and information
  • Entropy and phase transitions in large networks
  • Decision-making and paradoxes
  • Quantum information geometry

    • Current Teaching

  • Data Analysis for Enterprise Modelling, 2nd year BSc, 2021--present.
  • Stochastic Calculus and Pricing Derivatives, MSc, 2014--present.
  • Artificial Intelligence and Applications, 3rd year BSc, 2010--present.
  • Functional Analysis, 3rd year BSc, developed in 2016.
  • Differential Equations, 3rd year BSc, developed in 2016--2020.3.
  • Knowledge Management Strategies, MSc, 2011--present.
  • Knowledge Discovery, MSc, 2006--2009.
  • Decision-Making and Management Support Systems, MSc BIT, 2002--2009.
  • Advanced Calculus, Pathfinder programme, summer 2005.
  • LaTeX workshop for PhD students, 2007--2009.

    • Current PhD students:

    Silviu Tudor Marc, Hyperparameter Control in Deep Learning Neural Networks. Director of studies.

    Completed PhD students:

    Chwalinski, P., Intrusion detection with Clustering and Information Theoretic measurements.  Director of studies.  Completed in 2014.

    Parvizi, A., Automatic Concept Addition to Ontologies Aided by Semantics.  Director of studies.  Completed in 2012.

    Nadh, K., Modelling Associative Memory with Cell-Assemblies. 2nd supervisor.  Completed in 2011.

    Jamshed, F., Symbol Grounding with Cell-Assemblies.  2nd supervisor.  Completed in 2011.

    Yurinskiy, D., A Dempster-Shafer Theory Inspired Logic.  Director of studies.  Completed in 2009.


    Biography

    Roman Belavkin obtained MSc in Physics from the Moscow State University and PhD in Computer Science from the University of Nottingham.  His research interests span several areas including geometric analysis of optimal and learning systems, dynamics of information, value of information, quantum information, topology of information, geometry and combinatorics of mutation and recombination of sequences, optimal control of evolutionary algorithms, cognitive modelling.  Roman joined Middlesex University in 2002, where he participated in several research projects and organized research seminars of the Artificial Intelligence group.  From 2009 Roman has been the Principle Investigator of the EPSRC project `SANDPIT: Evolution as an Information Dynamic System', which was led by Middlesex University in collaboration with Universities of Manchester, Keele and Warwick.  In this project, Roman developed a theory of optimal control of mutation rate in evolutionary systems, and the team discovered plastic mutation rates in microbes (https://doi.org/skb , https://doi.org/cb9s).  Roman's current work is on geometric and dynamic value of information theory, which has applications in parameter control and optimization of learning, adaptive and evolving systems.  Roman has many international collaborations: He has been an associate member of the `Centre of Applied Optimization' in the University of Florida, USA; his collaboration with Tokyo University of Science was recognized in 2014 by the award from the university's president Professor Akira Fujishima.  Roman has been a keynote speaker at many international conferences, workshops and research seminars.  He also serves on the editorial board of the `Optimization Letters' and `SN Operations Research Forum' journals.

    Publications

    View publications