Defense Event

Combining Disparate Information for Machine Learning

Ko-Jen (Mark) Hsiao

Monday, April 14, 2014
3:00pm - 5:00pm
3316 EECS

Add to Google Calendar

About the Event

This dissertation considers information fusion for four different types of machine learning problems: anomaly detection, information retrieval, collaborative filtering and structure learning for time series, and focuses on a common theme -- the benefit to combining disparate information resulting in improved algorithm performance. In this dissertation, several new algorithms and applications to real-world datasets are presented. First, a novel approach called Pareto Depth Analysis (PDA) is proposed for combining different dissimilarity metrics for anomaly detection. PDA is applied to video-based anomaly detection of pedestrian trajectories. Next, following a similar idea, we propose to use a similar Pareto Front method for a multiple-query information retrieval problem when different queries represent different semantic concepts. Pareto Front information retrieval is applied to multiple query image retrieval. Then, we extend a recently proposed collaborative retrieval approach to incorporate complementary social network information, an approach we call Social Collaborative Retrieval (SCR). SCR is applied to a music recommendation system that combines both user history and friendship network information to improve recall and weighted recall performance. Finally, we propose a framework that combines time series data at different time scales and offsets for more accurate estimation of multiple precision matrices. We propose a general fused graphical lasso approach to jointly estimate these precision matrices. The framework is applied to modeling financial time series data.

Additional Information

Sponsor(s): Prof. Alfred O. Hero III

Open to: Public