Dr Roman Belavkin


Dr Roman Belavkin
NameDr Roman Belavkin
Job titleAssociate Professor in Informatics
Research institute
Primary appointmentComputer Science
Email addressr.belavkin@mdx.ac.uk
ORCIDhttps://orcid.org/0000-0002-2356-1447
Contact categoryResearcher

Biography

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.

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.

Education and qualifications

Grants

Adaptive landscapes of antibiotic resistance: population size and `survival-of-the-flattest'
01 Aug 2015
BB/M021106/1
BBSRC
The theory and practice of evolvability: Effects and mechanisms of mutation rate
01 Feb 2014
BBSRC
SANDPIT: Evolution as an Information Dynamic System
01 Jan 2010
EP/H031936/1
EPSRC
Natural Language Parsing with Cell Assemblies: computational linguistics with attractor nets
01 Jan 2006
EP/DO59720
EPSRC
Research Network on Blind Source Separation and Independent Component Analysis
01 Apr 2005
EP/C005554/1
EPSRC

Prizes and Awards

Evidence to public body

External activities

Research outputs

Value of information in the mean-square case and its application to the analysis of financial time-series forecast

Belavkin, R., Pardalos, P. and Principe, J. 2023. Value of information in the mean-square case and its application to the analysis of financial time-series forecast. Simos, D., Rasskazova, V., Archetti, F., Kotsireas, I. and Pardalos, P. (ed.) 16th International Conference on Learning and Intelligent Optimization. Milos Island, Greece 05 - 10 Jun 2022 Cham Springer. https://doi.org/10.1007/978-3-031-24866-5_39

Value of information in the binary case and confusion matrix

Belavkin, R., Pardalos, P. and Principe, J. 2022. Value of information in the binary case and confusion matrix. 41st International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering. Paris, France 18 - 22 Jul 2022 MDPI. pp. 1-9 https://doi.org/10.3390/psf2022005008

Theory of Information and its Value

Stratonovich, R. Belavkin, R., Pardalos, P. and Principe, J. (ed.) 2020. Theory of Information and its Value. Springer.

Environmental pleiotropy and demographic history direct adaptation under antibiotic selection

Gifford, D., Krašovec, R., Aston, E., Belavkin, R., Channon, A. and Knight, C. 2018. Environmental pleiotropy and demographic history direct adaptation under antibiotic selection. Heredity. 121 (5), pp. 438-448. https://doi.org/10.1038/s41437-018-0137-3

Opposing effects of final population density and stress on Escherichia coli mutation rate

Krašovec, R., Richards, H., Gifford, D., Belavkin, R., Channon, A., Aston, E., McBain, A. and Knight, C. 2018. Opposing effects of final population density and stress on Escherichia coli mutation rate. The ISME journal. 12 (12), pp. 2981-2987. https://doi.org/10.1038/s41396-018-0237-3

Relation between the Kantorovich-Wasserstein metric and the Kullback-Leibler divergence

Belavkin, R. 2018. Relation between the Kantorovich-Wasserstein metric and the Kullback-Leibler divergence. IGAIA IV 2016: Information Geometry and Its Applications. Liblice, Czech Republic 12 - 17 Jun 2016 Springer International Publishing. https://doi.org/10.1007/978-3-319-97798-0_15

Critical mutation rate has an exponential dependence on population size for eukaryotic-length genomes with crossover

Aston, E., Channon, A., Belavkin, R., Gifford, D., Krašovec, R. and Knight, C. 2017. Critical mutation rate has an exponential dependence on population size for eukaryotic-length genomes with crossover. Scientific Reports. 7 (1). https://doi.org/10.1038/s41598-017-14628-x

Spontaneous mutation rate is a plastic trait associated with population density across domains of life

Krašovec, R., Richards, H., Gifford, D., Hatcher, C., Faulkner, K., Belavkin, R., Channon, A., Aston, E., McBain, A. and Knight, C. 2017. Spontaneous mutation rate is a plastic trait associated with population density across domains of life. PLOS Biology. 15 (8). https://doi.org/10.1371/journal.pbio.2002731

Monotonicity of fitness landscapes and mutation rate control

Belavkin, R., Channon, A., Aston, E., Aston, J., Krašovec, R. and Knight, C. 2016. Monotonicity of fitness landscapes and mutation rate control. Journal of Mathematical Biology. 73 (6-7), pp. 1491-1524. https://doi.org/10.1007/s00285-016-0995-3

Asymmetric topologies on statistical manifolds

Belavkin, R. 2015. Asymmetric topologies on statistical manifolds. 2nd International Conference on Geometric Science of Information. Palaiseau, France 28 - 30 Oct 2015 Springer. https://doi.org/10.1007/978-3-319-25040-3_23

Asymmetry of risk and value of information

Belavkin, R. 2014. Asymmetry of risk and value of information. in: Vogiatzis, C., Walteros, J. and Pardalos, P. (ed.) Dynamics of Information Systems: Computational and Mathematical Challenges Springer.

On variational definition of quantum entropy

Belavkin, R. 2014. On variational definition of quantum entropy. 34th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (MaxEnt 2014). Clos Lucé, Amboise, France 21 - 26 Sep 2014 American Institute of Physics. https://doi.org/10.1063/1.4905979

Where antibiotic resistance mutations meet quorum-sensing

Krašovec, R., Belavkin, R., Aston, J., Channon, A., Aston, E., Rash, B., Kadirvel, M., Forbes, S. and Knight, C. 2014. Where antibiotic resistance mutations meet quorum-sensing. Microbial Cell. 1 (7), pp. 250-252. https://doi.org/10.15698/mic2014.07.158

Mutation rate plasticity in rifampicin resistance depends on Escherichia coli cell–cell interactions

Krašovec, R., Belavkin, R., Aston, J., Channon, A., Aston, E., Rash, B., Kadirvel, M., Forbes, S. and Knight, C. 2014. Mutation rate plasticity in rifampicin resistance depends on Escherichia coli cell–cell interactions. Nature Communications. 5, pp. 1-8. https://doi.org/10.1038/ncomms4742

Local semantic indexing for resource discovery on overlay network using mobile agents

Singh, M., Cheng, X. and Belavkin, R. 2014. Local semantic indexing for resource discovery on overlay network using mobile agents. International Journal of Computational Intelligence Systems. 7 (3), pp. 432-455. https://doi.org/10.1080/18756891.2013.856257

Law of Cosines and Shannon-Pythagorean theorem for quantum information

Belavkin, R. 2013. Law of Cosines and Shannon-Pythagorean theorem for quantum information. in: Nielsen, F. and Barbaresco, F. (ed.) Geometric Science of Information : First International Conference, GSI 2013, Paris, France, August 28-30, 2013. Proceedings Berlin Springer Verlag.

Minimum of information distance criterion for optimal control of mutation rate in evolutionary systems

Belavkin, R. 2013. Minimum of information distance criterion for optimal control of mutation rate in evolutionary systems. in: Accardi, L., Freudenberg, W. and Ohya, M. (ed.) Quantum Bio-Informatics V : Proceedings of the Quantum Bio-Informatics 2011. Tokyo University of Science, Japan, 7 – 12 March 2011 World Scientific.

Dynamics of information and optimal control of mutation in evolutionary systems

Belavkin, R. 2012. Dynamics of information and optimal control of mutation in evolutionary systems. in: Sorokin, A., Murphey, R., Thai, M. and Pardalos, P. (ed.) Dynamics of Information Systems: Mathematical Foundations New York Springer.

Optimal measures and Markov transition kernels

Belavkin, R. 2013. Optimal measures and Markov transition kernels. Journal of Global Optimization. 55 (2), pp. 387-416. https://doi.org/10.1007/s10898-012-9851-1

Maximal connectivity and constraints in the human brain

Belavkin, R. 2012. Maximal connectivity and constraints in the human brain. in: Pardalos, P., Coleman, T. and Xanthopoulos, P. (ed.) Optimization and data analysis in biomedical informatics New York Springer.

Mutation and optimal search of sequences in nested Hamming spaces

Belavkin, R. 2011. Mutation and optimal search of sequences in nested Hamming spaces. IEEE Information Theory Workshop (ITW). Paraty, Brazil 16 - 20 Oct 2011 IEEE. pp. 90-94 https://doi.org/10.1109/ITW.2011.6089592

Critical mutation rate has an exponential dependence on population size

Channon, A., Aston, E., Day, C., Belavkin, R. and Knight, C. 2011. Critical mutation rate has an exponential dependence on population size. Lenaerts, T., Giacobini, M., Bersini, H., Bourgine, P., Dorigo, M. and Doursat, R. (ed.) ECAL 2011: The 11th European Conference on Artificial Life. Paris, France 08 - 12 Aug 2011 MIT Press. pp. 117-124 https://doi.org/10.7551/978-0-262-29714-1-ch021

Theory and practice of optimal mutation rate control in Hamming spaces of DNA sequences

Belavkin, R., Channon, A., Aston, E., Aston, J. and Knight, C. 2011. Theory and practice of optimal mutation rate control in Hamming spaces of DNA sequences. Lenaerts, T., Giacobini, M., Bersini, H., Bourgine, P., Dorigo, M. and Doursat, R. (ed.) ECAL 2011: The 11th European Conference on Artificial Life. Paris, France 08 - 12 Aug 2011 MIT Press. pp. 85-92 https://doi.org/10.7551/978-0-262-29714-1-ch017

On evolution of an information dynamic system and its generating operator

Belavkin, R. 2012. On evolution of an information dynamic system and its generating operator. Optimization Letters. 6 (5), pp. 827-840. https://doi.org/10.1007/s11590-011-0325-z

Conflict resolution and learning probability matching in a neural cell-assembly architecture

Belavkin, R. and Huyck, C. 2011. Conflict resolution and learning probability matching in a neural cell-assembly architecture. Cognitive Systems Research. 12 (2), pp. 93-101. https://doi.org/10.1016/j.cogsys.2010.08.003

Resource discovery using mobile agents

Singh, M., Cheng, X. and Belavkin, R. 2010. Resource discovery using mobile agents. Frontier of Computer Science and Technology (FCST), 2010 Fifth International Conference. Changchun, Jilin Province 18 - 22 Aug 2010 IEEE. pp. 72 -77 https://doi.org/10.1109/FCST.2010.93

Information trajectory of optimal learning

Belavkin, R. 2010. Information trajectory of optimal learning. in: Hirsch, M., Pardalos, P. and Murphey, R. (ed.) Dynamics of Information Systems: Theory and Applications Springer.

Emergence of rules in cell assemblies of fLIF neurons.

Belavkin, R. and Huyck, C. 2008. Emergence of rules in cell assemblies of fLIF neurons. The 18th European Conference on Artificial Intelligence. University of Patras, Greece 21 - 25 Jul 2008

Utility and value of information in cognitive science, biology and quantum theory.

Belavkin, R. 2010. Utility and value of information in cognitive science, biology and quantum theory. in: Accardi, L., Freudenberg, W. and Ohya, M. (ed.) Quantum bio-informatics III: from quantum information to bio-informatics. London World Scientific.

A model of probability matching in a two-choice task based on stochastic control of learning in neural cell-assemblies.

Belavkin, R. and Huyck, C. 2009. A model of probability matching in a two-choice task based on stochastic control of learning in neural cell-assemblies. 9th International conference on cognitive modelling {ICCM 2009]. University of Manchester 24 - 26 Jul 2009

Bounds of optimal learning

Belavkin, R. 2009. Bounds of optimal learning. 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning. Sheraton Music City Hotel, Nashville, TN, USA Nashville, TN, USA IEEE.

Counting with neurons: rule application with nets of fatiguing leaking integrate and fire neurons.

Huyck, C. and Belavkin, R. 2006. Counting with neurons: rule application with nets of fatiguing leaking integrate and fire neurons. 7th International Conference on Cognitive Modelling. Trieste, Italy pp. 142-147

The duality of utility and information in optimally learning systems

Belavkin, R. 2008. The duality of utility and information in optimally learning systems. IEEE Systems, Man and Cibernetics Society, UK and Republic of Ireland: 7th conference on cybernetics intelligent systems, 2008.. Middlesex University, London 08 - 09 Sep 2008 London IEEE.

Do neural models scale up to a human brain?

Belavkin, R. 2007. Do neural models scale up to a human brain? International Joint Conference on Neural Networks (IJCNN 2007). Orlando, Florida 12 - 17 Aug 2007 IEEE.

Towards a theory of decision-making without paradoxes.

Belavkin, R. 2006. Towards a theory of decision-making without paradoxes. Fum, D., Missier, F. and Stocco, A. (ed.) Proceedings of the Seventh International Conference on Cognitive Modeling. Trieste, Italy 05 - 08 Apr 2006 Trieste, Italy Edizioni Goliardiche. pp. 38-43

Towards a theory of decision-making with paradoxes.

Belavkin, R. 2006. Towards a theory of decision-making with paradoxes. Proceedings of the Seventh International Conference on Cognitive Modelling. Trieste, Italy 2006 pp. 38-43

Acting irrationally to improve performance in stochastic worlds

Belavkin, R. 2005. Acting irrationally to improve performance in stochastic worlds. Bramer, M., Coenen, F. and Allen, T. (ed.) 25th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence. Cambridge, UK 2005 Springer. pp. 305-316 https://doi.org/10.1007/978-1-84628-226-3_23

Entropy and information in models of learning behaviour

Belavkin, R. 2005. Entropy and information in models of learning behaviour. AISB Quarterly. 119, pp. 5-5.

On relation between emotion and entropy

Belavkin, R. 2004. On relation between emotion and entropy. AISB'04 Symposium on Emotion, Cognition and Affective Computing. Leeds UK pp. 1-8

OPTIMIST: A new conflict resolution algorithm for ACT-R.

Belavkin, R. and Ritter, F. 2004. OPTIMIST: A new conflict resolution algorithm for ACT-R. Sixth International Conference on Cognitive Modelling. Mahwah, NJ pp. 40-45

Learning behaviour patterns of classroom and distance students using flexible learning resources.

Dimitrova, M., Belavkin, R., Milankovic-Atkinson, M., Sadler, C. and Murphy, A. 2003. Learning behaviour patterns of classroom and distance students using flexible learning resources. in: Lee, K. and Mitchell, K. (ed.) International conference on computers in education 2003: a conference of the Asia-Pacific chapter of the association for the advancement of computing in education (AACE). Hong Kong ICCE.

The use of entropy for analysis and control of cognitive models

Belavkin, R. and Ritter, F. 2003. The use of entropy for analysis and control of cognitive models. The Fifth International Conference on Cognitive Modelling. Bamberg, Germany 2003 pp. 21-26

Conflict resolution by random estimated costs

Belavkin, R. 2003. Conflict resolution by random estimated costs. 17th European Simulation Multiconference. Nottingham UK pp. 105-110
  • 1558
    total views of outputs
  • 88
    total downloads of outputs
  • 28
    views of outputs this month
  • 11
    downloads of outputs this month