Spike-Timing-Dependent Plasticity for Bernoulli Message Passing

Sepideh Adamiat, Wouter M. Kouw, Bert de Vries
12/19/2025
q-bio.NCcs.LGcs.NE

No official code found. Best implementation: biaslab/stdp-bernoulli-message-passing (2 stars, last commit 2025-09-10).

Abstract

Bayesian inference provides a principled framework for understanding brain function, while neural activity in the brain is inherently spike-based. This paper bridges these two perspectives by designing spiking neural networks that simulate Bayesian inference through message passing for Bernoulli messages. To train the networks, we employ spike-timing-dependent plasticity, a biologically plausible mechanism for synaptic plasticity which is based on the Hebbian rule. Our results demonstrate that the network's performance closely matches the true numerical solution. We further demonstrate the versatility of our approach by implementing a factor graph example from coding theory, illustrating signal transmission over an unreliable channel.

View on arXivView PDF

Code Implementations(1)

biaslab/stdp-bernoulli-message-passingCommunity67%

Code for the paper Spike-Timing-Dependent Plasticity for Bernoulli Message Passing

20Jupyter NotebookSep 10, 20251 years ago

Similar Papers

Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks

84% match1 repo2025

Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays

83% match2025

Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits

82% match1 repo112023

Spiking neural networks with Hebbian plasticity for unsupervised representation learning

82% match2023

Predictive Spike Timing Enables Distributed Shortest Path Computation in Spiking Neural Networks

82% match2025

Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian

81% match2026

Cite this paper

@article{adamiat2025spiketimingdependent,
  title  = {Spike-Timing-Dependent Plasticity for Bernoulli Message Passing},
  author = {Sepideh Adamiat and Wouter M. Kouw and Bert de Vries},
  year   = {2025},
  eprint = {2512.23728},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.23728v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.23728.svg)](https://codeofpaper.com/paper/2512.23728)

Discussion