Towards interpreting recurrent neural networks through probabilistic abstraction

• Main Authors: DONG, Guoliang, WANG, Jingyi, SUN, Jun, ZHANG, Yang, WANG, Xinyu, DAI, Ting, DONG, Jin Song, WANG, Xingen
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Abstraction; Interpretation; Probabilistic automata; Recurrent neural networks; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5947; https://ink.library.smu.edu.sg/context/sis_research/article/6950/viewcontent/1909.10023.pdf
• Institution: Singapore Management University

Neural networks are becoming a popular tool for solving many realworld 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 conse...