Nonlinear Dynamical Systems Feedforward Neural Network Perspectives

by Sandberg, Irwin W.; Lo, James T.; Fancourt, Craig L.; Principe, José; C.; Katagiri, Shigeru; Haykin, Simon

• ISBN13: 9780471349112
• ISBN10: 0471349119
• Edition: 1st
• Format: Hardcover
• Copyright: 2001-02-21
• Publisher: Wiley-Interscience

Summary

The first truly up-to-date look at the theory and capabilities of nonlinear dynamical systems that take the form of feedforward neural network structures Considered one of the most important types of structures in the study of neural networks and neural-like networks, feedforward networks incorporating dynamical elements have important properties and are of use in many applications. Specializing in experiential knowledge, a neural network stores and expands its knowledge base via strikingly human routes-through a learning process and information storage involving interconnection strengths known as synaptic weights. In Nonlinear Dynamical Systems: Feedforward Neural Network Perspectives, six leading authorities describe recent contributions to the development of an analytical basis for the understanding and use of nonlinear dynamical systems of the feedforward type, especially in the areas of control, signal processing, and time series analysis. Moving from an introductory discussion of the different aspects of feedforward neural networks, the book then addresses: * Classification problems and the related problem of approximating dynamic nonlinear input-output maps * The development of robust controllers and filters * The capability of neural networks to approximate functions and dynamic systems with respect to risk-sensitive error * Segmenting a time series It then sheds light on the application of feedforward neural networks to speech processing, summarizing speech-related techniques, and reviewing feedforward neural networks from the viewpoint of fundamental design issues. An up-to-date and authoritative look at the ever-widening technical boundaries and influence of neural networks in dynamical systems, this volume is an indispensable resource for researchers in neural networks and a reference staple for libraries.

Author Biography

IRWIN W. SANDBERG is a chaired professor at the University of Texas at Austin.

Table of Contents

Preface	vii
Feedforward Neural Networks: An Introduction	1	(16)
Simon Haykin
Supervised Learning	2	(6)
Unsupervised Learning	8	(2)
Temporal Processing Using Feedforward Networks	10	(4)
Concluding Remarks	14	(3)
Uniform Approximation and Nonlinear Network Structures	17	(68)
Irwin W. Sandberg
Introduction	17	(2)
General Structures for Classification	19	(12)
Myopic Maps, Neural Network Approximations, and Volterra Series	31	(13)
Separation Conditions and Approximation of Discrete-Time and Discrete-Space Systems	44	(13)
Concluding Comments	57	(1)
Appendices	58	(27)
Robust Neural Networks	85	(18)
James T. Lo
Introduction	85	(3)
Preliminaries	88	(1)
General Risk-Sensitive Functionals	89	(1)
Approximation of Functions by MLPs	90	(2)
Approximation of Functions by RBFs	92	(1)
Formulation of Risk-Sensitive Identification of Systems	92	(2)
Series-Parallel Identification by Artificial Neural Networks (ANNs)	94	(1)
Parallel Identification of ANNs	95	(5)
Conclusion	100	(3)
Modeling, Segmentation, and Classification of Nonlinear Nonstationary Time Series	103	(120)
Craig L. Fancourt
Jose C. Principe
Introduction	103	(14)
Supervised Sequential Change Detection	117	(28)
Unsupervised Sequential Segmentation	145	(12)
Memoryless Mixture Models	157	(7)
Mixture Models for Processes with Memory	164	(12)
Gated Competitive Experts	176	(6)
Competitive Temporal Principal Component Analysis	182	(10)
Output-Based Gating Algorithms	192	(14)
Other Approaches	206	(3)
Conclusions	209	(14)
Application of Feedforward Networks to Speech	223	(72)
Shigeru Katagiri
Introduction	223	(2)
Fundamentals of Speech Signals and Processing Technologies	225	(16)
Fundamental Issues of ANN Design	241	(18)
Speech Recognition	259	(15)
Applications to Other Types of Speech Processing	274	(11)
Concluding Remarks	285	(10)
Index	295