中華資訊網路協會 Chinese Information & Networking Association

4675 Stevens Creek Blvd., Suite 101, Santa Clara, CA 95051

http://www.cina.org

 
 
CINA July Monthly Seminar 
 

Modern Machine Learning Theories & Child Learning

-- The untapped Artificial Intelligence Market

近朱者赤，近墨者黑

Date/Time: Saturday, July 31, 2004, 10am - 12pm

 10:00 am - 10:30 am Registration & Networking
 10:30 am - 12:00 pm Presentation, Q & A
Venue: Fenwick & West, LLP, 801 California Street, Mountain View, CA 94041
Speaker:  Professor Edward Chang, University of California, Santa Barbara
Fee:   Free for CINA Members; $10 for Non-members 
RSVP:   RSVP@cina.org

Abstract

Machine Learning is a discipline of Computer Science and Statistics, which trains a computer to improve its performance based on past experience. Several real-world applications (e.g., information categorization, chess playing, and data mining) have drawn benefits from machine learning techniques. This talk presents recent advances in Machine Learning for dealing with the challenges of small training-data pool, and imbalanced-data learning. The talk will also discuss the related market potentials and business opportunities.

Speaker Profile

Professor Edward Chang received his M.S. in Computer Science and PhD in Electrical Engineering at Stanford University in 1994 and 1999, respectively. He is now a tenured Associate Professor of Electrical Engineering and Computer Engineering at the University of California, Santa Barbara. His research activities are in the areas of multimedia (image/video) databases, machine learning, data mining, and high-performance IO systems. He is particularly interested in application of machine-learning theoretical approaches to fundamental problems in multimedia information retrieval.

Recent research contributions of his group include methods for learning multimedia query concepts via active learning, formulating distance functions via dynamic associations and kernel alignment, and categorizing and indexing high-dimensional image/video data. His perception-based image retrieval approach, which applies learning algorithms to capture complex, subjective image query-concepts, was recognized as a major breakthrough in CBIR in 2002 at the IEEE International Conference on Multimedia.

Professor Edward Chang has served on several conference program committees including ACM SIGMOD, ACM Multimedia, ACM CIKM, SIAM Data Mining, International Conference on Artificial Intelligence, International Conference on Computer Vision, IEEE Data Engineering, IEEE Multimedia, and etc. He co-chairs the annual ACM Video Surveillance and Sensor Networks Workshop in 2003 and 2004. He serves as an Associate Editor for IEEE Transactions on Knowledge and Data Engineering. Ed is a recipient of the IBM Faculty Partnership Award from 2000 to 2002, and the NSF Career Award in 2002. Ed is also a co-founder and the CTO of VIMA Technologies, which provides image searching and filtering solutions.