You are here: Home → Events → Sensitivity Based Generalization Error for Supervised Learning Problem with Applications in Model Selection and Feature Selection
Document Actions

Sensitivity Based Generalization Error for Supervised Learning Problem with Applications in Model Selection and Feature Selection

A Seminar by Visiting Professor Daniel S Yeung, School of Computer Science and Engineering, South China University of Technology, Guangzhou, P. R. China

What Seminar
When 2008-12-18
from 10:00 to 11:00
Where Billings Room (Room 3.04 - Level 3) EECE
Contact Name Dr David Huang
Contact Email
Contact Phone 6488 1543
Add event to calendar vCal
iCal

Generalization error model provides a theoretical support for a classifier's performance in terms of prediction accuracy. However, existing models give very loose error bounds. This explains why classification systems generally rely on experimental validation for their claims on prediction accuracy. In this talk we will revisit this problem and explore the idea of developing a new generalization error model based on the assumption that ....

More Information