Sujun Hong (Graduate School of System Engineering, Wakayama University)*; Hirotaka Hachiya (Wakayama University)PMLR Page
When using a point process, a specific form of model needs to be designed for intensity function, based on physical and mathematical prior-knowledge about the data. Recently, fully trainable deep learning-based approach has been developed for temporal point processes. This approach models a cumulative hazard function (CHF), which is capable of systematic computation of adaptive intensity function in a data-driven. However, this approach does not take the attribute information of events into account although many applications of point processes generate with a variety of marked information such as location, magnitude, and depth of seismic activity. To overcome this limitation, we propose a fully-trainable marked point process method, modeling decomposed CHFs for time and mark using multi-stream deep neural networks. In addition, we also propose to encode multiple marked information into a single image and extract necessary information adaptively without detailed knowledge about the data. We show the effectiveness of our proposed method through experiments with simulated toy data and real seismic data.