Loading...

Implementation of Accurate Bio-Inspired Spiking Neural Network Using Fuzzy Methods

Karimi, Abolghasem | 2018

581 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 51278 (55)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed; Haj Sadeghi, Khosrow
  7. Abstract:
  8. Neuron models are the elementary units, which determine the performance of an Artificial Spiking Neural Network (ASNN) as they are known to be a particular class of machine learning methods. The ASNNs that are inspired by the features of biological neurons and organizational structure of biological nervous system as the third generation of Artificial Neural Networks (ANN). This thesis concentrates on study of biologically plausible neuron; based on Fuzzy approach and tries to develop fuzzy state of Leaky Integrate and Fire (LIF) model, in order to resemble closely the neuron-electrical dynamics for ASNN in most efficient way. In this study, the Fuzzy methods including TAKAGI-SUGENO-KANG techniques applied the fuzzify behavior of an Excitatory Postsynaptic Potential (EPSP). Furthermore, the relationship between Neurotransmitters and ions as linguistic variable in one side and membrane potential in another side has been fuzzified whereas Resting Potential (RP), Inhibitory Post Synaptic Potential (IPSP), EPSP, Action Potential (AP). As per today’s researches and known neurons morphology, the synapses have a quiet big number of branches. This thesis describes independent behavior of a neuron apart from neurons morphology, however simplification in processing and mitigation of processing costs are taken into account
  9. Keywords:
  10. Spiking Neural Network ; Takagi-Sugeno"s Fuzzy Modeling ; Fuzzy Model ; Bioinspired Design ; Leaky Integrate and Fire (LIF) Fuzzy Model

 Digital Object List

 Bookmark

No TOC