Modeling Continuous-Time Event Data With Neural Temporal Point Processes
MCML Authors
Oleksandr Shchur
Dr.
* Former Member
Abstract
Oleksandr Shchur
Dr.
* Former Member
Abstract
Temporal point processes (TPPs) provide a natural framework for modeling continuous-time event data such as earthquake catalogs in seismology or spike trains in neuroscience. Unlike conventional TPP models, neural TPPs are able to capture complex patterns present in real-world event data. The two main themes of this thesis are design of flexible, tractable and efficient neural TPP models, and their applications to real-world problems.
BibTeXKey: Shc22