• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Graduate Program in Materials Science and Nanotechnology
      • Graduate Program in Materials Science and Nanotechnology - Master's degree
      • View Item
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Graduate Program in Materials Science and Nanotechnology
      • Graduate Program in Materials Science and Nanotechnology - Master's degree
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Evolutionary adaptation and dopamine modulated learning in Spiking Neural Networks

      Thumbnail
      Embargo Lift Date: 2022-01-09
      View / Download
      9.1 Mb
      Author(s)
      Efe, Abdurrezak
      Advisor
      Jahangirov, Seymur
      Date
      2021-07
      Publisher
      Bilkent University
      Language
      English
      Type
      Thesis
      Item Usage Stats
      349
      views
      145
      downloads
      Abstract
      Amidst the rise of Deep Learning (DL) in the last ten years, many decades with-standing problems such as image classification, machine translation and text generation received superhuman level solutions. Combining DL with other paradigms such as Reinforcement Learning (RL) led to even more astonishing achievements such as solving the game of Go, 3D Protein Folding and scene reconstruction. However, not only Artificial Neural Networks (ANNs) used in DL require a massive amount of data as the problems get complicated (curse of dimensionality) but also the learning algorithms used in ANNs such as backpropagation are biologically not plausible. On the other hand, Spiking Neural Networks (SNNs) are computationally powerful nonlinear dynamical systems that are biologically more credible. Thus, approaching problems using SNNs promises the possibility of transferring methods and discoveries from Neuroscience. In this work, we utilized a well known genetic algorithm called NeuroEvolution of Augmenting Topologies (NEAT) on SNNs to train agents which can solve various nonlinear problems such as XOR, pole balancing and food chasing. Afterwards, we ap-plied dopamine modulation on Spike-Timing Dependent Plasticity (STDP) and attested that dopamine modulated STDP can indeed solve harder problems such as discovering good and bad nutrition types while trying to catch and consume food. The gist of the problem is that the same food can be beneficial in one episode/trial and detrimental in another one. As a result, we have shown that NEAT applied to SNNs can solve various nonlinear tasks; however, it cannot solve problems where in-life adaptation and/or discovery is required.
      Keywords
      Spiking Neural Networks
      Dopamine modulation
      NEAT
      Reinforce-ment Learning
      Permalink
      http://hdl.handle.net/11693/76418
      Collections
      • Graduate Program in Materials Science and Nanotechnology - Master's degree 183
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCoursesThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCourses

      My Account

      Login

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the User and Access Services. Phone: (312) 290 1298
      © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy