“Can machines do more than learning?”

June 27, 2018 from 3:30 to 4:20 p.m. — Physics/Astronomy Auditorium, room A118

Shou-De Lin

Professor, Computer Science and Information Engineering (CSIE), Graduate Institute of Networking and Multimedia, National Taiwan University

Abstract

We all know that machines can learn. Given a sufficient amount of training data, a machine learns a function to predict the unseen instances. In this talk, I’ll introduce another set of tasks aimed at using computers to perform discovery and creative writing. For instance, I’ll describe how machines can identify users and items across domains without training examples, write lyrics that strike a balance on the creativity and regulation, and so on.

Bio

A photo of Shou-De LinShou-de Lin is currently a full professor in the CSIE department of National Taiwan University (NTU). He holds a BS degree in the Electrical Engineering Department from National Taiwan University, an MS-EE degree from the University of Michigan, an MS degree in Computational Linguistics, and a PhD in Computer Science, both from the University of Southern California. He leads the Machine Discovery and Social Network Mining Lab at NTU.

Before joining NTU, he was a post-doctoral research fellow at the Los Alamos National Lab. Professor Lin’s research includes the areas of machine learning and data mining, social network analysis, and natural language processing. His international recognition includes the best paper award at the Institute of Electrical and Electronics Engineers (IEEE) Web Intelligence Conference (2003), the Google Research Award in 2007, Microsoft Research Awards in 2008, 2015, 2016, merit paper awards at the Conference on Technologies and Applications of Artificial Intelligence (TAAI) in 2010, 2014, and 2016, a best paper award at the IEEE/Association for Computing Machinery (ACM) International Conference on Advances in Social Networks Analysis and Mining in 2011, and a U.S. aerospace Air Force Office of Scientific Research/Asian Office of Aerospace Research and Development research award granted for five years.

He is probably the all-time winner in the Data Mining and Knowledge Discovery competition (ACM KDD Cup), leading or co-leading the NTU team to win five championships. He also led a team to win the ACM Websearch and Data Mining (WSDM) Cup in 2016. He has served as the senior program chair for the Special Interest Group on Knowledge Discovery and Data Mining and area chair for the Association for Computational Linguistics. He is currently the associate editor for the International Journal on Social Network Mining, the Journal of Information Science and Engineering, and the International Journal of Computational Linguistics and Chinese Language Processing. He is also a freelance writer for Scientific American.