Spike-Timing-Dependent Plasticity for Bernoulli Message Passing
This work addresses the problem of bridging Bayesian inference with biologically plausible neural mechanisms for researchers in computational neuroscience and machine learning, though it appears incremental as it applies known methods to a specific domain.
The paper tackled the challenge of implementing Bayesian inference in spiking neural networks by using spike-timing-dependent plasticity for Bernoulli message passing, achieving performance that closely matches the true numerical solution.
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.