用脉冲神经网络模拟贝叶斯推理，实现可靠消息传递。
Spike-Timing-Dependent Plasticity for Bernoulli Message Passing
- 基于脉冲时序可塑性训练脉冲网络，模拟贝叶斯消息传递。
- 性能接近真实数值解，验证了算法有效性。
- 适用于编码理论中的信道传输问题，具生物合理性。
贝叶斯推断为理解大脑功能提供了严谨框架，而大脑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，利用伯努利消息传递模拟贝叶斯推断，弥合了两者间的鸿沟。为训练网络，采用基于赫布规则的脉冲时序可塑性（STDP），这是一种生物上合理的突触可塑性机制。结果表明，网络性能与真实数值解高度吻合。进一步通过编码理论中的因子图实例，展示了在不可靠信道中信号传输的应用，验证了方法的通用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。