Skip to main content

Learning Heterogeneous Hidden Markov Random Fields.

Publication ,  Conference
Liu, J; Zhang, C; Burnside, E; Page, D
Published in: JMLR Workshop Conf Proc
2014

Hidden Markov random fields (HMRFs) are conventionally assumed to be homogeneous in the sense that the potential functions are invariant across different sites. However in some biological applications, it is desirable to make HMRFs heterogeneous, especially when there exists some background knowledge about how the potential functions vary. We formally define heterogeneous HMRFs and propose an EM algorithm whose M-step combines a contrastive divergence learner with a kernel smoothing step to incorporate the background knowledge. Simulations show that our algorithm is effective for learning heterogeneous HMRFs and outperforms alternative binning methods. We learn a heterogeneous HMRF in a real-world study.

Duke Scholars

Published In

JMLR Workshop Conf Proc

ISSN

1938-7288

Publication Date

2014

Volume

33

Start / End Page

576 / 584

Location

United States
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Liu, J., Zhang, C., Burnside, E., & Page, D. (2014). Learning Heterogeneous Hidden Markov Random Fields. In JMLR Workshop Conf Proc (Vol. 33, pp. 576–584). United States.
Liu, Jie, Chunming Zhang, Elizabeth Burnside, and David Page. “Learning Heterogeneous Hidden Markov Random Fields.” In JMLR Workshop Conf Proc, 33:576–84, 2014.
Liu J, Zhang C, Burnside E, Page D. Learning Heterogeneous Hidden Markov Random Fields. In: JMLR Workshop Conf Proc. 2014. p. 576–84.
Liu, Jie, et al. “Learning Heterogeneous Hidden Markov Random Fields.JMLR Workshop Conf Proc, vol. 33, 2014, pp. 576–84.
Liu J, Zhang C, Burnside E, Page D. Learning Heterogeneous Hidden Markov Random Fields. JMLR Workshop Conf Proc. 2014. p. 576–584.

Published In

JMLR Workshop Conf Proc

ISSN

1938-7288

Publication Date

2014

Volume

33

Start / End Page

576 / 584

Location

United States