Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor

Soft computing, a concept introduced by Zadeh[30], is in essence modeled after the human mind. Numerous studies have been done on the human cognitive process in attempts to understand the reasoning employed by humans as they try to solve complex problems. The results of these studies have lead to th...

Full description

Saved in:
Bibliographic Details
Main Author: Manpreet, Singh.
Other Authors: Quek Hiok Chai
Format: Final Year Project
Language:English
Published: 2013
Subjects:
Online Access:http://hdl.handle.net/10356/52055
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-52055
record_format dspace
spelling sg-ntu-dr.10356-520552019-12-10T14:07:38Z Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor Manpreet, Singh. Quek Hiok Chai School of Computer Engineering Centre for Computational Intelligence DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling Soft computing, a concept introduced by Zadeh[30], is in essence modeled after the human mind. Numerous studies have been done on the human cognitive process in attempts to understand the reasoning employed by humans as they try to solve complex problems. The results of these studies have lead to the development of a new branch of intelligent systems, systems that behave more so like humans. This new breed of systems exploit the tolerance for imprecision and uncertainty to achieve tractability, robustness and low solution cost. The major components of Soft Computing are Fuzzy Logic, Neural Network, Evolutionary Computing, Machine Learning and Probabilistic Reasoning. Using these components of Soft Computing in combination seem to deliver better results when solving real life problems, than if each component is used independently. ‘Neuro fuzzy computing’ is a prominent example of one such combination that has been particularly effective. The capability to combine human-like reasoning of fuzzy systems together with the connectionist structure and learning ability of neural networks, makes neuro fuzzy computing a popular framework for solving problems in soft computing [31]. Neuro-fuzzy hybridization is also commonly known as fuzzy neural networks (FNN) or neuro-fuzzy systems (NFS). Being able to provide insights about the symbolic knowledge embedded within the network is the primary advantage of neuro-fuzzy systems [32], making it of immense use in commercial and industrial applications. Having such wide reaching applications makes it of great interest to those in various scientific fields of study.   Bachelor of Engineering (Computer Science) 2013-04-22T03:08:51Z 2013-04-22T03:08:51Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/52055 en Nanyang Technological University 76 p. application/msword
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
Manpreet, Singh.
Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
description Soft computing, a concept introduced by Zadeh[30], is in essence modeled after the human mind. Numerous studies have been done on the human cognitive process in attempts to understand the reasoning employed by humans as they try to solve complex problems. The results of these studies have lead to the development of a new branch of intelligent systems, systems that behave more so like humans. This new breed of systems exploit the tolerance for imprecision and uncertainty to achieve tractability, robustness and low solution cost. The major components of Soft Computing are Fuzzy Logic, Neural Network, Evolutionary Computing, Machine Learning and Probabilistic Reasoning. Using these components of Soft Computing in combination seem to deliver better results when solving real life problems, than if each component is used independently. ‘Neuro fuzzy computing’ is a prominent example of one such combination that has been particularly effective. The capability to combine human-like reasoning of fuzzy systems together with the connectionist structure and learning ability of neural networks, makes neuro fuzzy computing a popular framework for solving problems in soft computing [31]. Neuro-fuzzy hybridization is also commonly known as fuzzy neural networks (FNN) or neuro-fuzzy systems (NFS). Being able to provide insights about the symbolic knowledge embedded within the network is the primary advantage of neuro-fuzzy systems [32], making it of immense use in commercial and industrial applications. Having such wide reaching applications makes it of great interest to those in various scientific fields of study.  
author2 Quek Hiok Chai
author_facet Quek Hiok Chai
Manpreet, Singh.
format Final Year Project
author Manpreet, Singh.
author_sort Manpreet, Singh.
title Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
title_short Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
title_full Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
title_fullStr Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
title_full_unstemmed Self-evolving Takagi-Sugeno-Kangfuzzy neural network with self-evolving forgetting factor
title_sort self-evolving takagi-sugeno-kangfuzzy neural network with self-evolving forgetting factor
publishDate 2013
url http://hdl.handle.net/10356/52055
_version_ 1681048319805095936