Hawkes process provides an effective statistical framework for analyzing the time-dependent interaction of neuronal spiking activities. Although utilized in many real applications, the classic Hawkes process is incapable of modelling inhibitory interactions among neurons. Instead, the nonlinear Hawkes process allows for a more flexible influence pattern with excitatory or inhibitory interactions. In this paper, three sets of auxiliary latent variables (P\'{o}lya-Gamma variables, latent marked Poisson processes and sparsity variables) are augmented to make functional connection weights in a Gaussian form, which allows for a simple iterative algorithm with analytical updates. As a result, an efficient expectation-maximization (EM) algorithm is derived to obtain the maximum a posteriori (MAP) estimate. We demonstrate the accuracy and efficiency performance of our algorithm on synthetic and real data. For real neural recordings, we show our algorithm can estimate the temporal dynamics of interaction and reveal the interpretable functional connectivity underlying neural spike trains.
翻译:Hawks 进程为分析神经刺激活动的时间性互动提供了一个有效的统计框架。 经典 Hawks 进程虽然在许多实际应用中被利用, 却无法模拟神经元之间的抑制性互动。 相反, 非线性 Hawks 进程允许以刺激性或抑制性互动来更灵活的影响模式。 在本文中, 三组辅助潜在变量( P\' {o}lya-Gamma 变量、 潜隐隐隐隐隐隐隐的Poisson 进程和孔径变量) 得到增强, 以高山形式使功能性连接权重成为高山形式, 从而可以使用简单的迭代用算法进行分析更新。 结果, 一种高效的预期- 最大化( EM) 算法被衍生来获得最高程度的事后( MAP) 估计值。 我们展示了合成和真实数据的算法的准确度和效率表现。 对于真正的神经记录, 我们的算法可以估计互动的时间动态, 并揭示出神经峰列下的可解释的功能性连接。