Sergey Muratov

Sergey Muratov

Belgrade, Serbia
2K followers 500+ connections

Activity

Join now to see all activity

Experience

  • Adapty Graphic

    Adapty

    Белград, Сербия

  • -

    Тбилиси, Грузия

  • -

    Тбилиси, Грузия

  • -

    Москва, Россия

  • -

    Москва, Россия

  • -

    Москва, Россия

Education

  • Skolkovo Institute of Science and Technology Graphic
  • -

    Spent a semester at MIT learning more about probabilistic approaches to machine learning and computer vision. Worked on projects about compositions of hierarchical bayesian networks and a convolutional neural network and submitted a Wikipedia article:
    https://en.wikipedia.org/wiki/Sparse_dictionary_learning

  • -

    Activities and Societies: KVN team, Freshmen events organization

    Pursued an Applied Math and Physics degree in order to get a deeper understanding of the driving forces behind the world around us. Was interested in discovering the working principles of the brain and studying neuroscience in general. Bachelor Thesis was dedicated to genetic algorithms applied to evolve artificial neural network's structure of the agent in a simulated environment with multiple goals.

    Full paper:…

    Pursued an Applied Math and Physics degree in order to get a deeper understanding of the driving forces behind the world around us. Was interested in discovering the working principles of the brain and studying neuroscience in general. Bachelor Thesis was dedicated to genetic algorithms applied to evolve artificial neural network's structure of the agent in a simulated environment with multiple goals.

    Full paper: https://mitpress.mit.edu/sites/default/files/titles/content/alife14/ch125.html

Licenses & Certifications

Volunteer Experience

Publications

  • Neuroevolution of sequential behavior in multi-goal navigation task

    Conference on the Synthesis and Simulation of Living Systems (ALIFE '14), pp. 771-777

    In this paper we consider a problem of evolutionary generation of behavioral sequences for a mobile robot in the environment with multiple goals. Many real-world tasks can be abstracted in terms of generation of actions sequences. To address this problem we utilize a neuroevolutionary algorithm, based on a neuron duplication, as a method to generate the robot's controller for multi-goal sequential navigation. We show that neuroevolution produces stable behavioral strategies that can be…

    In this paper we consider a problem of evolutionary generation of behavioral sequences for a mobile robot in the environment with multiple goals. Many real-world tasks can be abstracted in terms of generation of actions sequences. To address this problem we utilize a neuroevolutionary algorithm, based on a neuron duplication, as a method to generate the robot's controller for multi-goal sequential navigation. We show that neuroevolution produces stable behavioral strategies that can be successfully utilized even in the case of changing or randomized environment.

    Other authors
    See publication

Projects

Languages

  • Русский

    Native or bilingual proficiency

  • Английский

    Full professional proficiency

More activity by Sergey

View Sergey’s full profile

  • See who you know in common
  • Get introduced
  • Contact Sergey directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Sergey Muratov

Add new skills with these courses