Overview

Artificial neural networks possess several properties that make them particularly attractive for applications to modelling and control of complex non-linear systems. Among these properties are their universal approximation ability, their parallel network structure and the availability of on- and off-line learning methods for the interconnection weights. However, dynamic models that contain neural network architectures might be highly non-linear and difficult to analyze as a result. This work investigates the subject from a system theoretical point of view. However the mathematical theory that is required from the reader is limited to matrix calculus, basic analysis, differential equations and basic linear system theory. No preliminary knowledge of neural networks is explicitly required. The book presents both classical and novel network architectures and learning algorithms for modelling and control. Topics include non-linear system identification, neural optimal control, top-down model based neural control design and stability analysis of neural control systems. A major contribution of this book is to introduce NLq Theory as an extension towards modern control theory, in order to analyze and synthesize non-linear systems that contain linear together with static non-linear operators that satisfy a sector condition: neural state space control systems are an example. Moreover, it turns out that NLq Theory is unifying with respect to many problems arising in neural networks, systems and control.

Full Product Details

Author:   Johan A.K. Suykens ,  Joos P.L. Vandewalle ,  B.L. de Moor
Publisher:   Springer
Imprint:   Springer
Edition:   1996 ed.
Dimensions:   Width: 15.60cm , Height: 1.50cm , Length: 23.40cm
Weight:   1.180kg
ISBN:  

9780792396789

ISBN 10:   0792396782
Pages:   235
Publication Date:   31 December 1995
Audience:   College/higher education ,  Professional and scholarly ,  Postgraduate, Research & Scholarly ,  Professional & Vocational
Format:   Hardback
Publisher's Status:   Active
Availability:   In Print  
This item will be ordered in for you from one of our suppliers. Upon receipt, we will promptly dispatch it out to you. For in store availability, please contact us.

Table of Contents

1 Introduction.- 1.1 Neural information processing systems.- 1.2 ANNs for modelling and control.- 1.3 Chapter by Chapter overview.- 1.4 Contributions.- 2 Artificial neural networks: architectures and learning rules.- 2.1 Basic neural network architectures.- 2.2 Universal approximation theorems.- 2.3 Classical paradigms of learning.- 2.4 Conclusion.- 3 Nonlinear system identification using neural networks.- 3.1 From linear to nonlinear dynamical models.- 3.2 Parametrization by ANNs.- 3.3 Learning algorithms.- 3.4 Elements from nonlinear optimization theory.- 3.5 Aspects of model validation, pruning and regularization.- 3.6 Neural network models as uncertain linear systems.- 3.7 Examples.- 3.8 Conclusion.- 4 Neural networks for control.- 4.1 Neural control strategies.- 4.2 Neural optimal control.- 4.3 Conclusion.- 5 NLq Theory.- 5.1 A neural state space model framework for neural control design.- 5.2 NLq systems.- 5.3 Global asymptotic stability criteria for NLqs.- 5.4 Input/Output properties — l2 theory.- 5.5 Robust performance problem.- 5.6 Stability analysis: formulation as LMI problems.- 5.7 Neural control design.- 5.8 Control design: some case studies.- 5.9 NLqs beyond control.- 5.10 Conclusion.- 6 General conclusions and future work.- A.1 A generalization of Chua’s circuit.- B Fokker-Planck Learning Machine for Global Optimization.- B.1 Fokker-Planck equation for recursive stochastic algorithms.- B.2 Parametrization of the pdf by RBF networks.- B.3 FP machine: conceptual algorithm.- B.4 Examples.- B.5 Conclusions.

Reviews

Author Information

Tab Content 6

Author Website:  

Customer Reviews

Recent Reviews

No review item found!

Add your own review!

Countries Available

All regions