Towards explainable neural network fairness

• 主要作者: ZHANG, Mengdi
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: AI Fairness; Discrimination; Fairness Improvement; Bias Mitigation; AI Testing; Computer Sciences; OS and Networks
• 在線閱讀: https://ink.library.smu.edu.sg/etd_coll/547; https://ink.library.smu.edu.sg/context/etd_coll/article/1545/viewcontent/GPIS_AY2019_PhD_Mengdi_Zhang.pdf
• 機構: Singapore Management University

Neural networks are widely applied in solving many real-world problems. At the same time, they are shown to be vulnerable to attacks, difficult to debug, non-transparent and subject to fairness issues. Discrimination has been observed in various machine learning models, including Large Language Mode...