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.

翻译：贝叶斯推断为理解大脑功能提供了一个原则性框架，而大脑中的神经活动本质上是基于脉冲的。本文通过设计脉冲神经网络，使其通过消息传递对伯努利消息进行贝叶斯推断模拟，从而架起了这两种视角之间的桥梁。为训练网络，我们采用脉冲时序依赖可塑性——一种基于赫布法则、具有生物合理性的突触可塑性机制。我们的结果表明，网络性能与真实数值解高度吻合。通过实现编码理论中的一个因子图示例，我们进一步展示了本方法的通用性，该示例说明了信号在不可靠信道上的传输过程。