Title :
Variational Bayes for non-Gaussian autoregressive models
Author :
Penny, W.D. ; Roberts, S.J.
Author_Institution :
Dept. of Eng. Sci., Oxford Univ., UK
Abstract :
We describe a variational Bayesian (VB) learning algorithm for Non-Gaussian Autoregressive (AR) models. The noise is modelled as a mixture of Gaussians rather than the usual single Gaussian. This allows different data points to be associated with different noise levels and effectively provides a robust estimation of AR coefficients. The VB framework is used to prevent overfitting and provides model order selection criteria both for AR order and noise model order. The algorithm is applied to synthetic data and to EEG
Keywords :
Bayes methods; estimation theory; learning (artificial intelligence); variational techniques; EEG; model order selection criteria; noise model order; non-Gaussian autoregressive models; robust estimation; synthetic data; variational Bayesian learning algorithm; Bayesian methods; Brain modeling; Cost function; Degradation; Electroencephalography; Gaussian noise; Gaussian processes; Least squares methods; Noise level; Noise robustness;
Conference_Titel :
Neural Networks for Signal Processing X, 2000. Proceedings of the 2000 IEEE Signal Processing Society Workshop
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6278-0
DOI :
10.1109/NNSP.2000.889370
