Beiyang Intelligence Forum

The Problem of Explaining DNN

10/05/2020 13:29

Neural Network Fairness: Testing and Verification

SUN, Jun is currently an associate professor at Singapore Management University (SMU). He received Bachelor and PhD degrees in computing science from National University of Singapore (NUS) in 2002 and 2006. In 2007, he received the prestigious LEE KUAN YEW postdoctoral fellowship. He has been a faculty member since 2010. He was a visiting scholar at MIT from 2011-2012. Jun's research interests include software engineering, formal methods, program analysis and cyber-security. He is the co-founder of the PAT model checker. To this date, he has more than 200 journal articles or peer-reviewed conference papers, many of which are published at top-tier venues. His academic papers have won many international conference awards, and he is also the organizer of many international conferences.

Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and consequently trusting them in making critical decisions. Towards interpreting neural networks, several approaches have been proposed to extract simple deterministic models from neural networks. The results are not encouraging (e.g., low accuracy and limited scalability), fundamentally due to the limited expressiveness of such simple models. In this lecture, the speaker will introduce us to the latest approach of extracting probabilistic automata for interpreting an important class of neural networks.


Contact Us

Address:Building 55, College of Intelligence and Computing, Tianjin University Beiyangyuan Campus, No. 135 Yaguan Road, Jinnan District, Tianjin, 300350

Copyright©2017 College of Intelligence and Computing