Over the past decade, interest in computational or non-symbolic artificial intelligence has grown. The algorithms involved have the ability to learn from past experience, and therefore have significant potential in the adaptive control of signals and systems. This book focuses on the theory and applications of learning algorithms-stochastic learning automata; artificial neural networks; and genetic algorithms, evolutionary strategies, and evolutionary programming. Hybrid combinations of various algorithms are also discussed.
Chapter 1 provides a brief overview of the topics discussed and organization of the text. The first half of the book (Chapters 2 through 4) discusses the basic theory of the learning algorithms, with one chapter devoted to each type. In the second half (Chapters 5 through 7), the emphasis is on a wide range of applications drawn from adaptive signal processing, system identification, and adaptive control problems in telecommunication networks.
Learning Algorithms: Theory and Applications in Signal Processing, Control and Communications is an excellent text for final year undergraduate and first year graduate students in engineering, computer science, and related areas. Professional engineers and everyone involved in the application of learning techniques in adaptive signal processing, control, and communications will find this text a valuable synthesis of theory and practical application of the most useful algorithms.
Sprache
Verlagsort
Verlagsgruppe
Zielgruppe
Für höhere Schule und Studium
Für Beruf und Forschung
<li>Engineers
</li><li>Computer scientists
</li><li>Control/systems operators
</li><li>Senior undergraduate/graduate students in engineering, computer science, and related areas</li>
Illustrationen
Maße
Höhe: 235 mm
Breite: 156 mm
Gewicht
ISBN-13
978-0-8493-7896-6 (9780849378966)
Schweitzer Klassifikation
Introduction
Stochastic Learning Automata
Introduction
Stochastic Learning Automata
Stochastic Automata
The Environment
Norms of Behavior
Learning Algorithms
Standard Learning Algorithms
Discretised Learning Algorithms
S-Model Learning Schemes
Interconnected Automata
Hierarchical Learning Automata
Automata Games
Summary
Artificial Neural Networks
Introduction
Basic Concepts of Artificial Neural Nets
Architecture and Learning Algorithms
MLP Architecture
Radial Basis Function Nets
Kohonen Self-Organization Net
Reinforcement Learning Neural Nets
Generalization and Network Selection
Inductive Generalization
Statistical Generalization
Summary
Genetic and Evolutionary Optimization
Introduction
Genetic Algorithms
Introduction
Standard Genetic Operations
Adaptive Extensions of Genetic Algorithms
Evolutionary Strategies
Introduction
Standard Evolutionary Strategies
Improved Evolutionary Strategies
Evolutionary Programming
Introduction
Salient Features
Adaptive Extensions to Evolutionary Programming
Summary
Applications in Signal Processing
Introduction
Adaptive Digital Filtering using Stochastic Learning Automata
Introduction
Simulation Configuration
Simulation Results
Adaptive Digital Filtering using Genetic and Evolutionary Optimization
Introduction
Simulation Configuration
Simulation Results
Summary
Applications in Systems Control
Introduction
Representation of Nonlinear Systems
Nonlinear System Identification with Artificial Neural Nets
Static Nonlinear Mappings
Dynamic Systems with only Static Nonlinearity
Identification of Systems with Nonlinear Dynamics
Chaotic Time Series Prediction
Summary
Applications in Communications
Introduction
Access Control in Broadband ISDN
Introduction
The Call Access Control of ATM
Adaptive Call Access Control Strategies
Simulation Results and Discussion
Adaptive Equalization
Problem Definition
Minimum Phase Channel and Equalizers
Artificial Neural Networks for Channel Equalization
Dynamic Routing in Communication Networks
Circuit-Switched Networks
Packet-Switched Networks
Simulation Studies
Summary
Index
