Kar-ann Toh
School of Electrical and Electronic Engineering College of Engineering, Yonsei University, Seoul, South Korea
Kar-Ann Toh is a full professor in the School of Electrical and Electronic Engineering at Yonsei University, South Korea. His research interests include biometrics, pattern classification, optimization and neural networks. He is a co-inventor of a US patent and has made several PCT filings related to biometric applications. Besides being an active member in publications (PAMI, Machine Learning, Neural Computation etc), Dr. Toh has served as a member of advisory board and technical program committee for international conferences related to biometrics and artificial intelligence. He is currently a senior member of IEEE, an associate editor of IEEE-TIFS, Pattern Recognition Letters and IET Biometrics.
Talk : Linear and Advanced Classifier Methods for Biometric Applications
In this talk, we will first go through a brief
account on important developments in pattern classification and subsequently
zoom in to a new branch of linear methods for classification. In view of the
discrepancy between the frequently adopted least-squares error measure and the
actual classification error count needed, we seek a classification error
formulation for direct cost minimization. By approximating the nonlinear
counting step function using a quadratic link, we show that the classification
error rate minimization is deterministically solvable. Consequently, this
classification-based learning will be shown to be related to existing
classifiers such as Fisher's Linear Discriminant Analysis, Least Squares Error
and ROC-based learning in terms of mere data scaling. The effectiveness of the
methodology shall be demonstrated through multimodal application
examples." |