Reproduce “Probabilistic Inference of Binary Markov Random Fields in Spiking Neural Networks through Mean-field Approximation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yajing Zheng, Shanshan Jia, Zhaofei Yu, Tiejun Huang, Jian K. Liu, Yonghong Tian
The paper shows how a spiking recurrent neural network can implement mean-field marginal inference in binary Markov random fields. Each unit represents a pixel belief, while recurrent connections encode pairwise interactions and local inputs encode evidence; its rate dynamics match the mean-field update. On 5%-corrupted handwritten images, denoising matches mean-field results, within this approximation and tested scope.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.