HKBU  |  SCI  |  BUniPort  |  Library  |  Alumni  |  Job Vacancies  |  Intranet  |  Sitemap        
Undergraduate Admissions
Taught Postgraduate Admissions
Research Postgraduate Admissions
Job Vacancies
News & Achievements
Research Highlights
Contact & Direction

Department of Computer Science Seminar
2009 Series

Feature Extraction from semi-structured Documents; and the Encoding of Temporal Graphs (Seminar 2 of 4)

Dr. Markus Hagenbuchner
Department of Computer Science
Hong Kong Baptist University

Date: October 12, 2009 (Monday)
Time: 2:30 - 4:00 pm
Venue: SCT909, Cha Chi Ming Science Tower, Ho Sin Hang Campus

Frank Rosenfeld's vision was the development of artificial systems which exhibit intelligent, human like behavior. He suggested that this was best achieved by simulating the brain by means of computer technology. This was 50 years ago. Much research has since been done in simulating neural systems on computer systems. Despite such efforts, artificial neural systems are yet to exhibit any form of intelligent behavior. Thus this area of research remains one of the most exciting in computer science and also one with the greatest potential for future successes. This series of seminars will introduce the current state-of-the-art in the research on artificial neural systems. It will be shown how current artificial systems can learn from data whose complexity is greater than those that can be comprehended by a human brain. Such capability allows the solving of numerous practical, real world problems which used to be very hard to solve. We will also provide a direction for future research in this area.

This is the second seminar in a series of four seminars. The topic of this second seminar will be discuss open issues in feature extraction from semi-structured documents such as documents from the World Wide Web or scientific documents. It will be shown that such documents are most appropriately represented by graph structures. It will also be illustrated how one can deal with dynamic documents. Dynamic documents are documents which change over time (for example, Web documents that are regularly updated). The situation results in corresponding graph representations which change with time. We will show how such a sequence of graphs can be modeled with the help of computers.

These are introductory seminars. Attendees of the seminars do not need to have prior knowledge in artificial neural systems.

Dr Markus Hagenbuchner will present the seminar. A case study will be presented by a guest speaker (Dr Rowena Chau) from the Monash University in Australia.

Markus Hagenbuchner holds a PhD (Computer Science, University of Wollongong, Australia). He is currently a senior lecturer in the School of Computer Science and Software Engineering at the University of Wollongong, Australia. He joint the machine learning research area in 1992, started to focus his research activities on Neural Networks for the graph structured domain in 1998, and pioneered the development of Self-Organizing Maps for structured data. His contribution to the development of a Self-Organizing Map for graphs led to winning the international competition on document mining on several occasions.

He is a team leader of the machine learning group at the University of Wollongong. He has been the co-chair for the AI-08 conference, and is a program committee member for ANNPR 2010. He has been a reviewer of international standing for the Australian Research Council since 2004, and has been an invited guest speaker at various international venues. His current research interest is on the development of supervised and unsupervised machine learning methods for the processing of complex data structures in data mining applications.

********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
Slides (Dr. Markus Hagenbuchner)  Slides (Ms. Rowena Chau)
Copyright © 2021. All rights reserved.Privacy Policy
Department of Computer Science, Hong Kong Baptist University
Hong Kong Baptist University