Show simple item record

dc.contributor.authorOh, Sang Min
dc.contributor.authorRehg, James M.
dc.contributor.authorBalch, Tucker
dc.contributor.authorDellaert, Frank
dc.date.accessioned2011-04-19T20:14:13Z
dc.date.available2011-04-19T20:14:13Z
dc.date.issued2005-07
dc.identifier.citationOh, S.M., Rehg, J.M., Balch, T., & Dellaert, F. (2005). Data-Driven MCMC for Learning and Inference in Switching Linear Dynamic Systems. Proceedings of the National Conference on Artificial Intelligence (AAAI 2005), 9-13 July 2005, 944-949.en_US
dc.identifier.urihttp://hdl.handle.net/1853/38601
dc.description©2005. American Association for Artificial Intelligence. The original publication is available at: www.aaai.orgen_US
dc.description.abstractSwitching Linear Dynamic System (SLDS) models are a popular technique for modeling complex nonlinear dynamic systems. An SLDS has significantly more descriptive power than an HMM, but inference in SLDS models is computationally intractable. This paper describes a novel inference algorithm for SLDS models based on the Data- Driven MCMC paradigm. We describe a new proposal distribution which substantially increases the convergence speed. Comparisons to standard deterministic approximation methods demonstrate the improved accuracy of our new approach. We apply our approach to the problem of learning an SLDS model of the bee dance. Honeybees communicate the location and distance to food sources through a dance that takes place within the hive. We learn SLDS model parameters from tracking data which is automatically extracted from video. We then demonstrate the ability to successfully segment novel bee dances into their constituent parts, effectively decoding the dance of the bees.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectConvergence speeden_US
dc.subjectData-driven MCMCen_US
dc.subjectDatasetsen_US
dc.subjectHoneybee danceen_US
dc.subjectSwitching linear dynamic systemen_US
dc.titleData-Driven MCMC for Learning and Inference in Switching Linear Dynamic Systemsen_US
dc.typePost-printen_US
dc.typeProceedings
dc.contributor.corporatenameGeorgia Institute of Technology. Center for Robotics and Intelligent Machines
dc.contributor.corporatenameGeorgia Institute of Technology. College of Computing
dc.publisher.originalAAAI Press


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record