NCKU Math Colloquium / RCTS Seminar
|TITLE||Use Machine Learning to Crunch Big Data|
Generating, collecting and saving data are no longer to be expensive tasks. As a consequence, data deluge has created the Big Data Era. How to extract generalizable knowledge from data has attracted people’s attention from many research areas, industrial and business domains. In this talk, we will give a brief introduction to Big Data and introduce the basic concept of machine learning to show why it has been considered as a major solution for big data analytics models. I will share two successful applications, malicious URL filtering and detecting in-situ identity fraud on Facebook to demonstrate the power of machine learning methodology. |
Dr. Yuh-Jye Lee received the PhD degree in Computer Science from the University of Wisconsin-Madison in 2001. He is a professor of Department of Computer Science and Information Engineering at National Taiwan University of Science and Technology. He also serves as a principal investigator at the Intel-NTU Connected Context Computing Center. His research is primarily rooted in optimization theory and spans a range of areas including network and information security, machine learning, data mining, big data, numerical optimization and operations research. During the last decade, Dr. Lee has developed many learning algorithms in supervised learning, semi-supervised learning and unsupervised learning as well as linear/nonlinear dimension reduction. His recent major research is applying machine learning to information security problems such as network intrusion detection, anomaly detection, malicious URLs detection and legitimate user identification. Currently, he focus on online learning algorithms for dealing with large scale datasets, stream data mining and behavior based anomaly detection for the needs of big data and IoT security problems.