Time: 2018-12-12 10：00-12：00

Venue: Room 203 Lecture Hall

abstract：Representation-based classification (RC) methods such as sparse RC (SRC) have attracted great interest in pattern recognition, computer vision and remote sensing in recent years. Despite their empirical success, few theoretical results have been reported to justify their effectiveness. Establishing theoretical guarantees for RC methods can help us have a better understanding of when and why they can succeed in classification. This talk will introduce the algorithm, theory and applications of SRC, with an emphasis on the recent theoretical results.