Please join us this Tuesday (31 Jan, 6p) in AE 217 as IDEA PhD student Xiao Shou leads us in a discussion of his work, "Learning and Inference from Temporal Event Sequences."
TITLE: Learning and Inference from Temporal Event Sequences
DESCRIPTION: Event sequences are ubiquitous in our life. Common examples include customer transaction and electronic health records where customers and patients perform certain actions over time. The study of event sequences plays a cruc ial role in understanding and capturing the dynamics of event transitions and have practical real life implications such as predication on next arrival of certain event of interest, reasoning about how events influence each other, and quantifying the effect of influence from one events on another. In this talk, I introduce some novel tools of dealing with event sequences related to the learning and inference problems, leveraging state-of-the-art machine learning and deep learning paradigms.
BIO: Xiao Shou is fifth PhD student in Applied Mathematics. He also dual majors in CS (Masters). Currently, his research interests lie in the area of (neural) sequence models, causal reasoning, and graphical event models which is the intersection of graphical models and temporal point processes.
Xiao Shou is fifth PhD student in Applied Mathematics. He also dual majors in CS (Masters). Currently, his research interests lie in the area of (neural) sequence models, causal reasoning, and graphical event models which is the intersection of graphical models and temporal point processes.