Spike-Timing-Dependent Plasticity for Bernoulli Message Passing
- Sepideh Adamiat(Corresponding author),
- ,
- ,
- ,
- ,
- ,
- ,
- Lazy Dynamics B.V.
Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-reviewOpen access
Information
Output type
Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-reviewHost publication Subtitle
6th International Workshop, IWAI 2025, Montreal, QC, Canada, October 15–17, 2025, Revised Selected PapersOriginal language
EnglishPages from-to (Number of pages)
Pages 99-112 (14 pages)Publication milestones
- Accepted/In press - 2026
- Published - 01/04/2026
Publication status
Published - 01/04/2026
Place of publication
ChamPublisher
Springer, Netherlands, United States, United Kingdom, Germany, Italy, France, Austria, India, Switzerland, China, JapanPublication series
- Publication series name: Communications in Computer and Information Science (CCIS)
ISSN (Print): 1865-0929
ISSN (Electronic): 1865-0937
Volume: 2857
ISBN (Print)
978-3-032-16954-9ISBN (Electronic)
978-3-032-16955-6Host publication title
Active InferenceHost publication editors
- Mahault Albarracin
- David Benrimoh
- Christopher L. Buckley
- Pablo Lanillos
- Riddhi J. Pitliya
- Hideaki Shimazaki
- Ivilin Peev Stoianov
- Tim Verbelen
- Martijn Wisse
Funding Details
This work was carried out in the context of the BayesBrain project. We gratefully acknowledge financial support from the Eindhoven Artificial Intelligence Systems Institute (EAISI) at TU Eindhoven.
Related Event
Title
6th International Workshop on Active Inference, IWAI 2025
Event type
ConferenceDegree of recognition
International eventDate
15/10/2025 - 17/10/2025Location
MontrealCanada
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.
Documents and Links
Metrics
Metrics
SciVal
Author count
3
SciVal
Paper percentile
72
