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

DOI10.1016/J.NEUNET.2020.03.003MaRDI QIDQ1980397zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Yanyan Li

Publication date 8 September 2021

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1902.08411

zbMATH Keywords

probabilistic inferencemean-field approximationMarkov random fields (MRFs)recurrent neural networks (RNNs)spiking neural networks (SNNs)

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Stochastic processes (60G99)

Abstract: Recent studies have suggested that the cognitive process of the human brain is realized as probabilistic inference and can be further modeled by probabilistic graphical models like Markov random fields. Nevertheless, it remains unclear how probabilistic inference can be implemented by a network of spiking neurons in the brain. Previous studies have tried to relate the inference equation of binary Markov random fields to the dynamic equation of spiking neural networks through belief propagation algorithm and reparameterization, but they are valid only for Markov random fields with limited network structure. In this paper, we propose a spiking neural network model that can implement inference of arbitrary binary Markov random fields. Specifically, we design a spiking recurrent neural network and prove that its neuronal dynamics are mathematically equivalent to the inference process of Markov random fields by adopting mean-field theory. Furthermore, our mean-field approach unifies previous works. Theoretical analysis and experimental results, together with the application to image denoising, demonstrate that our proposed spiking neural network can get comparable results to that of mean-field inference.

Recommendations

• Neural network implementation of inference on binary Markov random fields with probability coding
• Belief Propagation in Networks of Spiking Neurons
• Spike-based probabilistic inference in analog graphical models using interspike-interval coding
• Learning probabilistic neural representations with randomly connected circuits
• Bayesian Spiking Neurons I: Inference

Cites work

• scientific article; zbMATH DE number 5284813 (Why is no real title available?)
• scientific article; zbMATH DE number 1983334 (Why is no real title available?)
• An introduction to variational methods for graphical models
• Bayesian Computation in Recurrent Neural Circuits
• Bayesian Spiking Neurons I: Inference
• Belief Propagation in Networks of Spiking Neurons
• Cortical Circuitry Implementing Graphical Models
• Graphical models, exponential families, and variational inference
• Modeling stereopsis via Markov random field
• Neural network implementation of inference on binary Markov random fields with probability coding
• Perception as Bayesian Inference
• Probabilistic graphical models.

Cited in

(6)

• Markov dependency based on Shannon's entropy and its application to neural spike trains
• Spike-based probabilistic inference in analog graphical models using interspike-interval coding
• Normalization for probabilistic inference with neurons
• Learning probabilistic neural representations with randomly connected circuits
• Neural network implementation of inference on binary Markov random fields with probability coding
• Belief Propagation in Networks of Spiking Neurons

This page was built for publication: Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1980397)