Adaptive Learning Methods for Nonlinear System Modeling

Adaptive Learning Methods for Nonlinear System Modeling introduces recent advances on adaptive algorithms and methods designed for nonlinear system modeling and identification. The book focuses on algorithms and methods that process data coming from an unknown nonlinear system. Such algorithms are based on an adaptive approach that allows the developer to estimate instant-by-instant (i.e., in an online manner) the nonlinearity introduced by the unknown system on the available data. This allows one to identify and model the unknown system, thus ensuring that the presence of nonlinearity in available data does not negatively affect performance.

Possible fields of the applications include, but are not limited to, Wireless Communications, Underwater Communications, Network Security, Nonlinear Modeling in Distributed Networks, Vehicular Networks, Active Noise Control, Information Forensics and Security and Nonlinear Modeling in Big Data, among others. This book is a valuable resource for researchers, PhD and post-graduate students, and those working in a variety of areas.

Presents key trends and future perspectives in the field of nonlinear signal processingProvides some code for both methods and application scenariosTackles state-of-the-art techniques in the very exciting area of online and adaptive nonlinear identificationHelps users understand the most effective methods in non-linear system modeling, suggesting the right methodology to solve a particular problem

1. Introduction

PART I – LINEAR-IN-THE-PARAMETERS NONLINEAR FILTERS 2. Orthogonal LIP Nonlinear Filters 3. Spline Adaptive Filters: Theory and Applications 4. Recent Advances on LIP Nonlinear Filters and Their Applications: Efficient Solutions and Significance Aware Filtering

PART II – ADAPTIVE ALGORITHMS IN THE REPRODUCING KERNEL HILBERT SPACE 5. Maximum Correntropy Criterion Based Kernel Adaptive Filters 6. Kernel Subspace Learning for Pattern Classification 7. A Random Fourier Features Perspective of KAFs with Application to Distributed Learning over Networks 8. Kernel-based Inference of Functions over Graphs

PART III – NONLINEAR MODELING WITH MULTIPLE LEARNING MACHINES 9. Online Nonlinear Modeling via Self-Organizing Trees 10. Adaptation and Learning Over Networks for Nonlinear System Modeling 11. Cooperative Filtering Architectures for Complex Nonlinear Systems

PART IV – NONLINEAR MODELING BY NEURAL NETWORKS 12. Echo State Networks for Multidimensional Data: Exploiting Noncircularity and Widely Linear Models 13. Identification of Short-Term and Long-Term Functional Synaptic Plasticity from Spiking Activities 14. Adaptive H∞ Tracking Control of Nonlinear Systems using Reinforcement Learning 15. Adaptive Dynamic Programming for Optimal Control of Nonlinear Distributed Parameter Systems