Neural Networks and Fuzzy Systems: Theory and Applications discusses theories that have proven useful in applying neural networks and fuzzy systems to real world problems. The book includes performance comparison of neural networks and fuzzy systems using data gathered from real systems. Topics covered include the Hopfield network for combinatorial optimization problems, multilayered neural networks for pattern classification and function approximation, fuzzy systems that have the same functions as multilayered networks, and composite systems that have been successfully applied to real world problems. The author also includes representative neural network models such as the Kohonen network and radial basis function network. New fuzzy systems with learning capabilities are also covered.
The advantages and disadvantages of neural networks and fuzzy systems are examined. The performance of these two systems in license plate recognition, a water purification plant, blood cell classification, and other real world problems is compared.
Auflage
Sprache
Verlagsort
Zielgruppe
Für höhere Schule und Studium
Für Beruf und Forschung
Research
Illustrationen
Maße
Höhe: 241 mm
Breite: 160 mm
Dicke: 20 mm
Gewicht
ISBN-13
978-0-7923-9814-1 (9780792398141)
DOI
10.1007/978-1-4615-6253-5
Schweitzer Klassifikation
1 Overview of Neural Networks.- 1.1 Brief History of Neural Network Research.- 1.2 Neural Network Models.- 1.3 Expectations for Neural Networks.- 2 The Hopfield Network.- 2.1 Definition of the Continuous Hopfield Network.- 2.2 Stability of Equilibrium Points.- 2.3 Suppression of Spurious States.- 2.4 Solution of the Hopfield Network.- 2.5 Variants of the Continuous Hopfield Network.- 2.6 Performance Evaluation for Traveling Salesman Problems and LSI Module Placement Problems.- Problems.- 3 Multilayered Networks.- 3.1 Network Training.- 3.2 Determination of the Network Structure.- 3.3 Synthesis of the Network.- 3.4 Pattern Classification by the Decision Tree Extracted from the Network.- 3.5 Acceleration of Training and Improvement of Generalization Ability.- Problems.- 4 Other Neural Networks.- 4.1 The Kohonen Network.- 4.2 Variants of Multilayered Networks.- 4.3 ART Models.- Problem.- 5 Overview of Fuzzy Systems.- 5.1 Fuzzy Sets.- 5.2 Fuzzy Rule Inference.- 5.3 Comparison of Neural Networks and Fuzzy Systems.- 5.4 Fuzzy Rule Extraction.- Problems.- 6 Fuzzy Rule Extraction for Pattern Classification from Numerical Data.- 6.1 Approximation by Cluster Centers.- 6.2 Approximation by Hyperboxes.- 6.3 Approximation by Polyhedrons.- 6.4 Performance Evaluation.- Problems.- 7 Fuzzy Rule Extraction for Function Approximation from Numerical Data.- 7.1 Clustering of Input Space.- 7.2 Clustering of Input and Output Spaces.- 7.3 Performance Evaluation of a Water Purification Plant and Time Series Prediction.- Problems.- 8 Composite Systems.- 8.1 Determining the Optimal Structure of the Composite Multilayered Network Classifier.- 8.2 Applications.- References.- Solutions to Problems.- Author Index.
