Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation. (June 2020)

• Record Type: Journal Article
• Authors: Zheng, Yajing; Jia, Shanshan; Yu, Zhaofei; Huang, Tiejun; Liu, Jian K.; Tian, Yonghong
• Is Part Of: Neural networks. Volume 126(2020)
• Page Start: 42
• Page End: 51
• Publication Date: 2020-06
• Subjects: Probabilistic inference -- Markov Random Fields (MRFs) -- Spiking Neural Networks (SNNs) -- Recurrent Neural Networks (RNNs) -- Mean-field approximation; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2020.03.003
• Languages: English
• ISSNs: 0893-6080

Abstract

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.