Spiking Neural Networks (SNNs) capture some of the efficiency of biological brains for inference and learning via the dynamic, online, event-driven processing of binary time series. Most existing learning algorithms for SNNs are based on deterministic neuronal models, such as leaky integrate-and-fire, and rely on heuristic approximations of backpropagation through time that enforce constraints such as locality. In contrast, probabilistic SNN models can be trained directly via principled online, local, update rules that have proven to be particularly effective for resource-constrained systems. This paper investigates another advantage of probabilistic SNNs, namely their capacity to generate independent outputs when queried over the same input. It is shown that the multiple generated output samples can be used during inference to robustify decisions and to quantify uncertainty -- a feature that deterministic SNN models cannot provide. Furthermore, they can be leveraged for training in order to obtain more accurate statistical estimates of the log-loss training criterion, as well as of its gradient. Specifically, this paper introduces an online learning rule based on generalized expectation-maximization (GEM) that follows a three-factor form with global learning signals and is referred to as GEM-SNN. Experimental results on structured output memorization and classification on a standard neuromorphic data set demonstrate significant improvements in terms of log-likelihood, accuracy, and calibration when increasing the number of samples used for inference and training.
翻译:Spik Neural 网络( SNN) 捕捉生物大脑的某些效率, 以便通过动态、 在线、 事件驱动的神经时间序列进行推断和学习。 多数 SNN 的现有学习算法都基于确定性神经模型, 如泄漏整合与火灾, 并依靠确定性 SNN 模型的背面偏差近似值, 以施加诸如地点等限制。 相比之下, 概率 SNN 模型可以直接通过原则性在线、 当地、 更新规则来培训, 事实证明这些规则对资源限制的系统特别有效。 本文调查了概率性 SNNN 的另一个优势, 即当询问同一输入时, 即它们产生独立产出的能力。 显示, 多个生成的产出样本可以在推断决定和量化不确定性的过程中使用。 确定性 SNNNN模型无法提供这一特征。 此外, 也可以利用这些模型进行培训, 以便获得对日志损失培训标准标准标准值标准值以及梯度进行更准确的统计估计。 具体地, 本文介绍了基于普遍预期- 和精确性 的精确性 数据化的在线学习规则, 将GEMmeximal- sal- slational- silizmillation 的模型作为全球 的系统化 的系统化 的系统化 的系统化 的系统化,, 的系统化 显示 的系统化 显示 的系统化 的系统化 数据 的系统化 。