Chen / Zhu / Hu System Parameter Identification

Information Criteria and Algorithms
1. Auflage 2013
ISBN: 978-0-12-404595-8
Verlag: Elsevier Science & Techn.
Format: EPUB
Kopierschutz: 6 - ePub Watermark

E-Book, Englisch, 266 Seiten

Recently, criterion functions based on information theoretic measures (entropy, mutual information, information divergence) have attracted attention and become an emerging area of study in signal processing and system identification domain. This book presents a systematic framework for system identification and information processing, investigating system identification from an information theory point of view. The book is divided into six chapters, which cover the information needed to understand the theory and application of system parameter identification. The authors' research provides a base for the book, but it incorporates the results from the latest international research publications. - Named a 2013 Notable Computer Book for Information Systems by Computing Reviews - One of the first books to present system parameter identification with information theoretic criteria so readers can track the latest developments - Contains numerous illustrative examples to help the reader grasp basic methods

Badong Chen received the B.S. and M.S. degrees in control theory and engineering from Chongqing University, in 1997 and 2003, respectively, and the Ph.D. degree in computer science and technology from Tsinghua University in 2008. He was a Post-Doctoral Researcher with Tsinghua University from 2008 to 2010, and a Post-Doctoral Associate at the University of Florida Computational NeuroEngineering Laboratory (CNEL) during the period October, 2010 to September, 2012. He is currently a professor at the Institute of Artificial Intelligence and Robotics (IAIR), Xi'an Jiaotong University. His research interests are in system identification and control, information theory, machine learning, and their applications in cognition and neuroscience.

Autoren/Hrsg.

Chen, Badong

Zhu, Yu

Hu, Jinchun

Principe, Jose C.

Leseproben

Symbols and Abbreviations
The main symbols and abbreviations used throughout the text are listed as follows.     absolute value of a real number     Euclidean norm of a vector     inner product     indicator function     expectation value of a random variable     first-order derivative of the function     second-order derivative of the function     gradient of the function with respect to     sign function     Gamma function     vector or matrix transposition     identity matrix     inverse of matrix     determinant of matrix     trace of matrix     rank of matrix     natural logarithm function     unit delay operator     real number space     -dimensional real Euclidean space     correlation coefficient between random variables and     variance of random variable     probability of event     Gaussian distribution with mean vector and covariance matrix     uniform distribution over interval     chi-squared distribution with degree of freedom     Shannon entropy of random variable     -entropy of random variable     -order Renyi entropy of random variable     -order information potential of random variable     survival information potential of random variable     -entropy of discrete random variable     mutual information between random variables and     KL-divergence between random variables and     -divergence between random variables and     Fisher information matrix     Fisher information rate matrix     probability density function     Mercer kernel function     kernel function for density estimation     kernel function with width     Gaussian kernel function with width     reproducing kernel Hilbert space induced by Mercer kernel     feature space induced by Mercer kernel     weight vector     weight vector in feature space     weight error vector     step size     sliding data length MSE    mean square error LMS    least mean square NLMS    normalized least mean square LS    least squares RLS    recursive least squares MLE    maximum likelihood estimation EM    expectation-maximization FLOM    fractional lower order moment LMP    least mean -power LAD    least absolute deviation LMF    least mean fourth FIR    finite impulse response IIR    infinite impulse response AR    auto regressive ADALINE    adaptive linear neuron MLP    multilayer perceptron RKHS    reproducing kernel Hilbert space KAF    kernel adaptive filtering KLMS    kernel least mean square KAPA    kernel affine projection algorithm KMEE    kernel minimum error entropy KMC    kernel maximum correntropy PDF    probability density function KDE    kernel density estimation GGD    generalized Gaussian density     symmetric -stable MEP    maximum entropy principle DPI    data processing inequality EPI    entropy power inequality MEE    minimum error entropy MCC    maximum correntropy criterion IP    information potential QIP    quadratic information potential CRE    cumulative residual entropy SIP    survival information potential QSIP    survival quadratic information potential KLID    Kullback–Leibler information divergence EDC    Euclidean distance criterion MinMI    minimum mutual information MaxMI    maximum mutual information AIC    Akaike’s information criterion BIC    Bayesian information criterion MDL    minimum description length FIM    Fisher information matrix FIRM    Fisher information rate matrix MIH    minimum identifiable horizon ITL    information theoretic learning BIG    batch information gradient FRIG    forgetting recursive information gradient SIG    stochastic information gradient SIDG    stochastic information divergence gradient SMIG    stochastic mutual information gradient FP    fixed point FP-MEE    fixed-point minimum error...