Variational Bayes for generalized autoregressive models

By Stephen J. Roberts, W. D. Penny. 2002

172 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Karl J. Friston
2. David M. Blei
3. Stefan J. Kiebel
4. Alp Kucukelbir
5. W. D. Penny
6. Jon D. McAuliffe
7. Jean Daunizeau
8. Nelson J. Trujillo-Barreto

In Statistics and Probability

1. Karl J. Friston
2. W. D. Penny
3. Stefan J. Kiebel
4. Alp Kucukelbir
5. Nelson J. Trujillo-Barreto
6. Jon D. McAuliffe
7. Christian F. Beckmann
8. Mark William Woolrich

Citations in the corpus

• Variational Inference: A Review for Statisticians (2016, methodology): “There have been many applications of variational inference to neuroscience, especially for autoregressive processes (Roberts and Penny 2002; Penny, Kiebel, and Friston 2003; Penny, Trujillo-Barreto, and Friston 2005; Flandin and Penny 2007; Harrison and Green 2010).”
• Bayesian fMRI time series analysis with spatial priors (2005, methodology): “…a lower bound on the model evidence (or equivalenty, minimise the KLdivergence between the true posterior and the approximate posterior) are given by (Roberts and Penny, 2002) exp[ ( )]( ) exp[ ( )] i i i i Iq I d = ∫ θθ θ θ where / /( ) ( ) log ( , )i i iI q p d= ∫θ θ Y θ θ and / iθ indicates…”
• Variational Bayesian inference for fMRI time series (2003, methodology): “Expressions for the KL divergences for the various densities are given in ( Roberts and Penny, 2002 ).”
• Linked independent component analysis for multimodal data fusion (2011, methodology): “Another alternative is to adaptively model the spatial smoothness in the data, much as the temporal smoothness in FMRI is estimated using autoregressive noise models (Woolrich et al., 2004; Roberts and Penny, 2002;Woolrich et al., 2001).”
• Comparing Dynamic Causal Models using AIC, BIC and Free Energy (2012, methodology): “…selection ability and recommended it be used for comparison of DCMs. Similar conclusions have been reached in earlier work comparing Free Energy with BIC in the context of non-Gaussian autoregressive modelling (Roberts and Penny, 2002) and Hidden Markov Modelling (Valente and Wellekens, 2004).”