The Block Diagonal Infinite Hidden Markov Model

Thomas Stepleton, Zoubin Ghahramani, Geoffrey Gordon, Tai-Sing Lee
; Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, PMLR 5:552-559, 2009.

Abstract

The Infinite Hidden Markov Model (IHMM) extends hidden Markov models to have a countably infinite number of hidden states \citeihmm,hdp. We present a generalization of this framework that introduces block-diagonal structure in the transitions between the hidden states. These blocks correspond to “sub-behaviors” exhibited by data sequences. In identifying such structure, the model classifies, or partitions, sequence data according to these sub-behaviors in an unsupervised way. We present an application of this model to artificial data, a video gesture classification task, and a musical theme labeling task, and show that components of the model can also be applied to graph segmentation.

Cite this Paper


BibTeX
@InProceedings{pmlr-v5-stepleton09a, title = {The Block Diagonal Infinite Hidden Markov Model}, author = {Thomas Stepleton and Zoubin Ghahramani and Geoffrey Gordon and Tai-Sing Lee}, booktitle = {Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics}, pages = {552--559}, year = {2009}, editor = {David van Dyk and Max Welling}, volume = {5}, series = {Proceedings of Machine Learning Research}, address = {Hilton Clearwater Beach Resort, Clearwater Beach, Florida USA}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v5/stepleton09a/stepleton09a.pdf}, url = {http://proceedings.mlr.press/v5/stepleton09a.html}, abstract = {The Infinite Hidden Markov Model (IHMM) extends hidden Markov models to have a countably infinite number of hidden states \citeihmm,hdp. We present a generalization of this framework that introduces block-diagonal structure in the transitions between the hidden states. These blocks correspond to “sub-behaviors” exhibited by data sequences. In identifying such structure, the model classifies, or partitions, sequence data according to these sub-behaviors in an unsupervised way. We present an application of this model to artificial data, a video gesture classification task, and a musical theme labeling task, and show that components of the model can also be applied to graph segmentation.} }
Endnote
%0 Conference Paper %T The Block Diagonal Infinite Hidden Markov Model %A Thomas Stepleton %A Zoubin Ghahramani %A Geoffrey Gordon %A Tai-Sing Lee %B Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2009 %E David van Dyk %E Max Welling %F pmlr-v5-stepleton09a %I PMLR %J Proceedings of Machine Learning Research %P 552--559 %U http://proceedings.mlr.press %V 5 %W PMLR %X The Infinite Hidden Markov Model (IHMM) extends hidden Markov models to have a countably infinite number of hidden states \citeihmm,hdp. We present a generalization of this framework that introduces block-diagonal structure in the transitions between the hidden states. These blocks correspond to “sub-behaviors” exhibited by data sequences. In identifying such structure, the model classifies, or partitions, sequence data according to these sub-behaviors in an unsupervised way. We present an application of this model to artificial data, a video gesture classification task, and a musical theme labeling task, and show that components of the model can also be applied to graph segmentation.
RIS
TY - CPAPER TI - The Block Diagonal Infinite Hidden Markov Model AU - Thomas Stepleton AU - Zoubin Ghahramani AU - Geoffrey Gordon AU - Tai-Sing Lee BT - Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics PY - 2009/04/15 DA - 2009/04/15 ED - David van Dyk ED - Max Welling ID - pmlr-v5-stepleton09a PB - PMLR SP - 552 DP - PMLR EP - 559 L1 - http://proceedings.mlr.press/v5/stepleton09a/stepleton09a.pdf UR - http://proceedings.mlr.press/v5/stepleton09a.html AB - The Infinite Hidden Markov Model (IHMM) extends hidden Markov models to have a countably infinite number of hidden states \citeihmm,hdp. We present a generalization of this framework that introduces block-diagonal structure in the transitions between the hidden states. These blocks correspond to “sub-behaviors” exhibited by data sequences. In identifying such structure, the model classifies, or partitions, sequence data according to these sub-behaviors in an unsupervised way. We present an application of this model to artificial data, a video gesture classification task, and a musical theme labeling task, and show that components of the model can also be applied to graph segmentation. ER -
APA
Stepleton, T., Ghahramani, Z., Gordon, G. & Lee, T.. (2009). The Block Diagonal Infinite Hidden Markov Model. Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, in PMLR 5:552-559

Related Material