Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Learning from Time Series for Health

Density-based Neural Temporal Point Processes for Heartbeat Dynamics

Sandya Subramanian · Bharath Ramsundar

Keywords: [ Neural Temporal Point Processes ] [ goodness-of-fit ] [ heart beat dynamics ] [ point processes ]


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.

Chat is not available.