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

DOI10.1016/J.NEUNET.2020.03.003zbMATH Open1471.92042DBLPjournals/nn/ZhengJYHLT20arXiv1902.08411OpenAlexW3011313139WikidataQ90518637 ScholiaQ90518637MaRDI QIDQ1980397FDOQ1980397

Authors: Yanyan Li 

Publication date: 8 September 2021

Published in: Neural Networks (Search for Journal in Brave)

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.

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

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

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)

Cites Work

• Graphical models, exponential families, and variational inference
• Probabilistic graphical models.
• Title not available (Why is that?)
• Belief Propagation in Networks of Spiking Neurons
• An introduction to variational methods for graphical models
• Bayesian Spiking Neurons I: Inference
• Title not available (Why is that?)
• Bayesian Computation in Recurrent Neural Circuits
• Perception as Bayesian Inference
• Neural network implementation of inference on binary Markov random fields with probability coding
• Modeling stereopsis via Markov random field
• Cortical Circuitry Implementing Graphical Models

Cited In (6)

• Neural network implementation of inference on binary Markov random fields with probability coding
• Markov dependency based on Shannon's entropy and its application to neural spike trains
• 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
• Normalization for probabilistic inference with 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)