Connectionists: Book announcement: "Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models", by D. Mandic and V. Goh

[Danilo Mandic]

Dear Colleagues,

people dealing with phase/asymmetry/synchrony related research in 
computational neuroscience may find this book very useful. The book is 
supported by Matlab code and datasources.

"Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely 
Linear and Neural Models", Wiley 2009

by D. Mandic and V. S. L. Goh

About the Book:
This book was written in response to the growing demand for a text that 
provides a unified treatment of linear and nonlinear complex valued 
adaptive filters, and methods for the processing of general complex 
signals (circular and noncircular). It brings together adaptive 
filtering algorithms for feedforward (transversal) and feedback 
architectures and the recent developments in the statistics of complex 
variable, under the powerful frameworks of CR (Wirtinger) calculus and 
augmented complex statistics. This offers a number of theoretical 
performance gains, which is illustrated on both stochastic gradient 
algorithms, such as the augmented complex least mean square (ACLMS), and 
those based on Kalman filters. This work is supported by a number of 
simulations using synthetic and real world data, including the 
noncircular and intermittent radar and wind signals.

Key features:

     * Provides theoretical and practical justification for converting 
many apparently real valued signal processing problems into the complex 
domain;
     * Offers a unified approach to the design of complex valued 
adaptive filters and temporal neural networks, based on augmented 
complex statistics and the duality between the bivariate and complex 
calculus (CR calculus);
     * Introduces augmented filtering algorithms based on widely linear 
models, making them suitable for processing both second order circular 
(proper) and noncircular (improper) complex signals;
     * Covers adaptive stepsizes, dynamical range reduction, validity of 
complex representations, and data driven time–frequency decompositions;
     * Includes extensive background material in appendices ranging from 
the theory of complex variables through to fixed point theory.

Complex valued signals play a central role in the fields of 
communications, radar, sonar, array, biomedical and environmental signal 
processing amongst others. This book will have wide appeal to 
researchers and practising engineers in these and related disciplines, 
and can also be used as lecture material for a course on adaptive filters.

Brief Table of Contents
1. The Magic of Complex Numbers
2. Why Signal Processing in the Complex Domain?
3. Adaptive Filtering Architectures
4. Complex Nonlinear Activation Functions
5. Elements of CR Calculus
6. Complex Valued Adaptive Filters
7. Adaptive Filters with Feedback
8. Filters with an Adaptive Stepsize
9. Filters with an Adaptive Amplitude of Nonlinearity
10. Data-reusing Algorithms for Complex Valued Adaptive Filters
11. Complex Mappings and Möbius Transformations
12. Augmented Complex Statistics
13. Widely Linear Estimation and Augmented CLMS (ACLMS)
14. Duality Between Complex Valued and Real Valued Filters
15. Widely Linear Filters with Feedback
16. Collaborative Adaptive Filtering
17. Adaptive Filtering Based on EMD
18. Validation of Complex Representations: Is This Worthwhile?

More information, Matlab sources, and Amazon link on:
http://www.commsp.ee.ic.ac.uk/~mandic/complexbook/
http://www.amazon.co.uk/dp/0470066350/
http://www.amazon.com/dp/0470066350/