State Inference in Variational Bayesian Nonlinear State-Space Models

Nonlinear source separation can be performed by inferring the state of a nonlinear state-space model. We study and improve the inference algorithm in the variational Bayesian blind source separation model introduced by Valpola and Karhunen in 2002. As comparison methods we use extensions of the Kalman filter that are widely used inference methods in tracking and control theory. The results in stability, speed, and accuracy favour our method especially in difficult inference problems.

[1]  C. M. Reeves,et al.  Function minimization by conjugate gradients , 1964, Comput. J..

[2]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[4]  최승진.  Nonlinear dynamic independent component analysis using state-space and neural network models , 1999 .

[5]  Richard M. Everson,et al.  Particle Filters for Non-Stationary ICA , 2000 .

[6]  M. Girolami,et al.  Advances in Independent Component Analysis , 2000, Perspectives in Neural Computing.

[7]  Neil J. Gordon,et al.  Editors: Sequential Monte Carlo Methods in Practice , 2001 .

[8]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[9]  Erkki Oja,et al.  Adaptive Algorithm for Blind Separation from Noisy Time-Varying Mixtures , 2001, Neural Computation.

[10]  Juha Karhunen,et al.  An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models , 2002, Neural Computation.

[11]  Rudolph van der Merwe,et al.  The Unscented Kalman Filter , 2002 .

[12]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[13]  Antti Honkela,et al.  Unsupervised Variational Bayesian Learning of Nonlinear Models , 2004, NIPS.

[14]  M. Psiaki.  Backward-Smoothing Extended Kalman Filter , 2005 .

[15]  T. Raiko,et al.  Learning nonlinear state-space models for control , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..