The Neurodynamics of Belief Propagation on Binary Markov Random Fields
Abstract
We rigorously establish a close relationship between message passing algorithms and models of neurodynamics by showing that the equations of a continuous Hop- (cid:2)eld network can be derived from the equations of belief propagation on a binary Markov random (cid:2)eld. As Hop(cid:2)eld networks are equipped with a Lyapunov func- tion, convergence is guaranteed. As a consequence, in the limit of many weak con- nections per neuron, Hop(cid:2)eld networks exactly implement a continuous-time vari- ant of belief propagation starting from message initialisations that prevent from running into convergence problems. Our results lead to a better understanding of the role of message passing algorithms in real biological neural networks.
Cite
Text
Ott and Stoop. "The Neurodynamics of Belief Propagation on Binary Markov Random Fields." Neural Information Processing Systems, 2006.Markdown
[Ott and Stoop. "The Neurodynamics of Belief Propagation on Binary Markov Random Fields." Neural Information Processing Systems, 2006.](https://mlanthology.org/neurips/2006/ott2006neurips-neurodynamics/)BibTeX
@inproceedings{ott2006neurips-neurodynamics,
title = {{The Neurodynamics of Belief Propagation on Binary Markov Random Fields}},
author = {Ott, Thomas and Stoop, Ruedi},
booktitle = {Neural Information Processing Systems},
year = {2006},
pages = {1057-1064},
url = {https://mlanthology.org/neurips/2006/ott2006neurips-neurodynamics/}
}