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

DOI10.1016/J.AMC.2016.12.025MaRDI QIDQ1735263zbMATH OpenOpenAlexFDO

Authors Zhaofei Yu, Feng Chen, Jianwu Dong

Publication date 28 March 2019

Published in Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.amc.2016.12.025

zbMATH Keywords

Markov random fieldsHopfield networkapproximate inferenceneural network implementationprobability coding

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation
• Exact Inferences in a Neural Implementation of a Hidden Markov Model
• Markovian neural networks
• A recurrent stochastic binary network
• Neural representation of probabilities for Bayesian inference

Cites work

• scientific article; zbMATH DE number 1983334 (Why is no real title available?)
• Bayesian Computation in Recurrent Neural Circuits
• Belief Propagation in Networks of Spiking Neurons
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Cortical Circuitry Implementing Graphical Models
• Graphical models, exponential families, and variational inference
• Improving the runtime of MRF based method for MRI brain segmentation
• Information capacity of the Hopfield model
• Modeling stereopsis via Markov random field
• Probabilistic graphical models.
• Sufficient Conditions for Convergence of the Sum–Product Algorithm

Cited in

(1)

• Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation

This page was built for publication: Neural network implementation of inference on binary Markov random fields with probability coding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1735263)