*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Name: Jyun-Yu Jiang
Date: Thursday, February 25, 2021 at 11:00 am
Link: https://bluejeans.com/6622130444
Title: Multi-scale Human Behavior Modeling with Heterogeneous Data
Abstract:
In this era of big data, massive data are generated from heterogeneous resources every day, which provides an unprecedented opportunity for deepening our understanding of complex human behaviors. Modeling human behaviors requires robust computational methods that can not only capture semantics and useful insights from sparse and heterogeneous data, but also unravel sophisticated human behaviors at different scales. Besides, the enormous data velocity and the unparalleled scale of deep models also pose significant challenges to efficiency. In this talk, I will demonstrate a collection of research results that systematically improve the ecosystem of human behavior modeling based on representation learning. I will present practical representation learning for heterogeneous data in various settings, and show how these representation learning methods actually fill a niche to comfortably model different behaviors with atomic, compositional, and explainable operations. Finally, I will discuss how the theory of human behaviors may conversely benefit machine learning algorithms.
Bio:
Jyun-Yu Jiang is a Ph.D. candidate in Computer Science at the University of California, Los Angeles (UCLA), advised by Prof. Wei Wang. Prior to joining UCLA, Jyun-Yu received his master’s and bachelor’s degrees from the National Taiwan University. His research focuses on developing effective and efficient computational methods to harness massive data to solve real-world problems. He has published broadly in machine learning, data mining, natural language processing, information retrieval, social science, and bioinformatics. He has summer internships at multiple research labs including Google, Microsoft, and FXPAL. Jyun-Yu is also the recipient of the UCLA Dissertation Year Fellowship from 2020-2021.
