Density-based Neural Temporal Point Processes for Heartbeat Dynamics
Keywords: neural temporal point processes, point processes, heart beat dynamics, goodness-of-fit
TL;DR: We introduce a goodness-of-fit framework to rigorously evaluate neural temporal point processes and test on heart beat dynamics data.
Abstract: Temporal point processes (TPPs) provide a natural mathematical framework for modeling heartbeats due to capturing underlying physiological inductive biases. In this work, we apply density-based neural TPPs to model heartbeat dynamics from 18 subjects. We adapt a goodness-of-fit framework from classical point process literature to Neural TPPs and use it to optimize hyperparameters, identify appropriate training sequence lengths to capture temporal dependencies, and demonstrate zero-shot predictive capability on heartbeat data.
Submission Number: 35
Loading