Neural network implementation of inference on binary Markov random fields with probability coding

Zhaofei Yu, Feng Chen and Jianwu Dong

Applied Mathematics and Computation, 2017, vol. 301, issue C, 193-200

Abstract: Markov random fields (MRF) underpin the solution to many problems in computational neuroscience. However, how the inference for MRF could be implemented with neural network is still an important open question. In this paper, we build the relationship between inference equation of MRF and the dynamic equation of the Hopfield network with probability coding. We prove that the membrane potential in the Hopfield network varying with respect to time can implement marginal probabilities inference on binary MRF. Theoretical analysis and experimental results show that our neural network can get comparable results as that of loopy belief propagation (LBP).

Keywords: Markov random fields; Approximate inference; Neural network implementation; Hopfield network; Probability coding (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300316307597
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:apmaco:v:301:y:2017:i:c:p:193-200

DOI: 10.1016/j.amc.2016.12.025

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().