AutoFocus: Interpreting attention-based neural networks by code perturbation

• Main Authors: BUI, Duy Quoc Nghi, YU, Yijun, JIANG, Lingxiao
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2019
• 主題: attention mechanisms; neural networks; algorithm classification; interpretability; code perturbation; programcomprehension; Software Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/4817; https://ink.library.smu.edu.sg/context/sis_research/article/5820/viewcontent/ase19autofocus.pdf

Despite being adopted in software engineering tasks, deep neural networks are treated mostly as a black box due to the difficulty in interpreting how the networks infer the outputs from the inputs. To address this problem, we propose AutoFocus, an automated approach for rating and visualizing the im...