Fuzzy Spiking Neural Networks

Master's Thesis , 2011 , 103 Pages , Grade: 8.84

Engineering - Computer Engineering

This dissertation presents an introductory knowledge to computational neuroscience and major emphasize on the branch of computational neuroscience called Spiking Neural Networks (SNNs). SNNs are also called the third generation neural networks. It has become now a major field of Soft Computing. In this we talk about the temporal characteristics’ of neuron and studied the dynamics of it. We have presented SNNs architecture with fuzzy reasoning capability. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train frequencies and behave in a similar manner as fuzzy membership functions.

The network of SNNs consists of three layers that is input, hidden and output layer. The topology of this network is based on Radial basis Network, which can be regarded as universal approximators. The input layer receives the input in the form of frequency which produces the spikes through linear encoding. There is another method of encoding called Poisson encoding; this encoding is used where the data is large. The hidden layer use Receptive Field (RF) to process the input and thus it is frequency selective. The output layer is only responsible for learning. The learning is based on local learning.

The XOR classification problem is used to test the capabilities of the network. There is a problem of continuous updating of weight arises. This issue of weight is resolved by using STDP window and fuzzy reasoning.

The dissertation demonstrates how it is possible to obtain fuzzy reasoning capability from biological models of spiking neurons. The fuzzy spiking neural network implements fuzzy rules by configuration of receptive fields, antecedent conjunction with excitatory and inhibitory connections, and inferencing via a biologically plausible supervised learning algorithm. In this way, the resulting system utilizes a higher level of knowledge representation.

Inhaltsverzeichnis

• Abstract
• List of Figures
• List of Tables
• Chapter 1: Introduction
• 1.1 Introduction
• 1.2 Motivation
• 1.3 Problem Statement
• 1.4 Objectives
• 1.5 Scope of the Dissertation
• 1.6 Organization of the Dissertation
• Chapter 2: Literature Review
• 2.1 Introduction
• 2.2 Artificial Neural Networks
• 2.3 Spiking Neural Networks
• 2.4 Fuzzy Logic
• 2.5 Fuzzy Spiking Neural Networks
• Chapter 3: Fuzzy Spiking Neural Networks
• 3.1 Introduction
• 3.2 Fuzzy Neuron Model
• 3.3 Fuzzy Synapse Model
• 3.4 Fuzzy Spiking Neural Network Architecture
• 3.5 Learning Algorithm
• Chapter 4: Simulation and Results
• 4.1 Introduction
• 4.2 Simulation Environment
• 4.3 Simulation Results
• Chapter 5: Conclusion and Future Work
• 5.1 Conclusion
• 5.2 Future Work
• Bibliography
• Appendix A: Source Code

Zielsetzung und Themenschwerpunkte

This dissertation aims to explore the potential of Fuzzy Spiking Neural Networks (FSNNs) as a novel computational paradigm for artificial intelligence. The work focuses on developing a comprehensive understanding of FSNNs, including their architecture, learning algorithms, and potential applications. The dissertation also presents a simulation study to evaluate the performance of FSNNs on a real-world problem.

• Fuzzy Logic and its integration with Spiking Neural Networks
• Development of a novel Fuzzy Spiking Neuron model
• Design and implementation of a learning algorithm for FSNNs
• Simulation and evaluation of FSNNs on a real-world problem
• Potential applications of FSNNs in various fields

Zusammenfassung der Kapitel

Chapter 1 provides an introduction to the dissertation, outlining the motivation, problem statement, objectives, scope, and organization of the work. Chapter 2 presents a comprehensive literature review on Artificial Neural Networks (ANNs), Spiking Neural Networks (SNNs), Fuzzy Logic, and Fuzzy Spiking Neural Networks (FSNNs). Chapter 3 delves into the details of FSNNs, including the Fuzzy Neuron Model, Fuzzy Synapse Model, FSNN architecture, and learning algorithm. Chapter 4 presents the simulation study conducted to evaluate the performance of FSNNs on a real-world problem. The chapter describes the simulation environment, simulation results, and analysis of the findings. Chapter 5 concludes the dissertation by summarizing the key findings, highlighting the contributions of the work, and outlining potential future research directions.

Schlüsselwörter

The keywords and focus themes of the text include Fuzzy Spiking Neural Networks, Fuzzy Logic, Spiking Neural Networks, Artificial Intelligence, Computational Neuroscience, Machine Learning, Neural Networks, Simulation, and Applications.

• College: Manav Rachna International University
• Course: Master of Technology (M.Tech)
• Grade: 8.84
• Author: Haider Raza (Author)
• Publication Year: 2011
• Pages: 103
• Catalog Number: V184731
• ISBN (eBook): 9783656096917
• ISBN (Book): 9783656097259
• Language: English
• Tags: fuzzy, spiking, neural, networks