Neuro-fuzzy architectures and hybrid learning
Author(s)
Bibliographic Information
Neuro-fuzzy architectures and hybrid learning
(Studies in fuzziness and soft computing, v. 85)
Physica-Verlag, c2002
Available at 9 libraries
  Aomori
  Iwate
  Miyagi
  Akita
  Yamagata
  Fukushima
  Ibaraki
  Tochigi
  Gunma
  Saitama
  Chiba
  Tokyo
  Kanagawa
  Niigata
  Toyama
  Ishikawa
  Fukui
  Yamanashi
  Nagano
  Gifu
  Shizuoka
  Aichi
  Mie
  Shiga
  Kyoto
  Osaka
  Hyogo
  Nara
  Wakayama
  Tottori
  Shimane
  Okayama
  Hiroshima
  Yamaguchi
  Tokushima
  Kagawa
  Ehime
  Kochi
  Fukuoka
  Saga
  Nagasaki
  Kumamoto
  Oita
  Miyazaki
  Kagoshima
  Okinawa
  Korea
  China
  Thailand
  United Kingdom
  Germany
  Switzerland
  France
  Belgium
  Netherlands
  Sweden
  Norway
  United States of America
Note
Includes bibliographical references (p. [241]-288)
Description and Table of Contents
Description
The advent of the computer age has set in motion a profound shift in our perception of science -its structure, its aims and its evolution. Traditionally, the principal domains of science were, and are, considered to be mathe matics, physics, chemistry, biology, astronomy and related disciplines. But today, and to an increasing extent, scientific progress is being driven by a quest for machine intelligence - for systems which possess a high MIQ (Machine IQ) and can perform a wide variety of physical and mental tasks with minimal human intervention. The role model for intelligent systems is the human mind. The influ ence of the human mind as a role model is clearly visible in the methodolo gies which have emerged, mainly during the past two decades, for the con ception, design and utilization of intelligent systems. At the center of these methodologies are fuzzy logic (FL); neurocomputing (NC); evolutionary computing (EC); probabilistic computing (PC); chaotic computing (CC); and machine learning (ML). Collectively, these methodologies constitute what is called soft computing (SC). In this perspective, soft computing is basically a coalition of methodologies which collectively provide a body of concepts and techniques for automation of reasoning and decision-making in an environment of imprecision, uncertainty and partial truth.
Table of Contents
1 Introduction.- 2 Description of Fuzzy Inference Systems.- 2.1 Fuzzy Sets.- 2.1.1 Basic Definitions.- 2.1.2 Operations on Fuzzy Sets.- 2.1.3 Fuzzy Relations.- 2.1.4 Operations on Fuzzy Relations.- 2.2 Approximxate Reasoning.- 2.2.1 Compositional Rule of Inference.- 2.2.2 Implications.- 2.2.3 Linguistic Variables.- 2.2.4 Calculus of Fuzzy Rules.- 2.2.5 Granulation and Fuzzy Graphs.- 2.2.6 Computing with Words.- 2.3 Fuzzy Systems.- 2.3.1 Rule-Based Fuzzy Logic Systems.- 2.3.2 The Mamdani and Logical Approaches to Fuzzy Inference.- 2.3.3 Fuzzy Systems Based on the Mamdani Approach.- 2.3.4 Fuzzy Systems Based on the Logical Approach.- 3 Neural Networks and Neuro-Fuzzy Systems.- 3.1 Neural Networks.- 3.1.1 Model of an Artificial Neuron.- 3.1.2 Multi-Layer Perceptron.- 3.1.3 Back-Propagation Learning Method.- 3.1.4 RBF Networks.- 3.1.5 Supervised and Unsupervised Learning.- 3.1.6 Competitive Learning.- 3.1.7 Hebbian Learning Rule.- 3.1.8 Kohonen's Self-Organizing Neural Network.- 3.1.9 Learning Vector Quantization.- 3.1.10 Other Types of Neural Networks.- 3.2 Fuzzy Neural Networks.- 3.3 Fuzzy Inference Neural Networks.- 4 Neuro-Fuzzy Architectures Based on the Mamdani Approach.- 4.1 Basic Architectures.- 4.2 General Form of the Architectures.- 4.3 Systems with Inference Based on Bounded Product.- 4.4 Simplified Architectures.- 4.5 Architectures Based on Other Defuzzification Methods.- 4.5.1 COS-Based Architectures.- 4.5.2 Neural Networks as Defuzzifiers.- 4.6 Architectures of Systems with Non-Singleton Fuzzifier.- 5 Neuro-Fuzzy Architectures Based on the Logical Approach.- 5.1 Mathematical Descriptions of Implication-Based Systems.- 5.2 NOCFS Architectures.- 5.3 OCFS Architectures.- 5.4 Performance Analysis.- 5.5 Computer Simulations.- 5.5.1 Function Approximation.- 5.5.2 Control Examples.- 5.5.3 Classification Problems.- 6 Hybrid Learning Methods.- 6.1 Gradient Learning Algorithms.- 6.1.1 Learning of Fuzzy Systems.- 6.1.2 Learning of Neuro-Fuzzy Systems.- 6.1.3 FLiNN - Architecture Based Learning.- 6.2 Genetic Algorithms.- 6.2.1 Basic Genetic Algorithm.- 6.2.2 Evolutionary Algorithms.- 6.3 Clustering Algorithms.- 6.3.1 Cluster Analysis.- 6.3.2 Fuzzy Clustering.- 6.4 Hybrid Learning.- 6.4.1 Combinations of Gradient Methods, GAs, and Clustering Algorithms.- 6.4.2 Hybrid Algorithms for Parameter Tuning.- 6.4.3 Rule Generation.- 6.5 Hybrid Learning Algorithms for Neuro-Fuzzy Systems.- 6.5.1 Examples of Hybrid Learning Neuro-Fuzzy Systems.- 6.5.2 Description of Two Hybrid Learning Algorithms for Rule Generation.- 6.5.3 Medical Diagnosis Applications.- 7 Intelligent Systems.- 7.1 Artificial and Computational Intelligence.- 7.2 Expert Systems.- 7.2.1 Classical Expert Systems.- 7.2.2 Fuzzy and Neural Expert Systems.- 7.3 Intelligent Computational Systems.- 7.4 Perception-Based Intelligent Systems.- 8 Summary.- List of Figures.- List of Tables.- References.
by "Nielsen BookData"