Under the supervision of Professor Gill Dobbie and Dr Vithya Yogarajan, this research project by Kejun Dai reviews frameworks for evaluating bias in artificial intelligence models. Situated within the broader “Ethical Computing” initiative led by Professor Gill Dobbie, this project seeks to identify strengths and gaps in current methodologies to ensure AI technologies advance in a manner that upholds ethical standards.
Title: How do we know those Artificial Intelligence models are fair? An overview of bias evaluating frameworks for AI models
Summary: Survey investigating the current state of bias evaluation frameworks for Artificial Intelligence models and their potential improvements. The methodology involves learning each framework and demonstrating its capabilities with benchmark experiments. The finding of the survey is that all frameworks prefer to approach fairness as equality rather than equity.
More technical information can be found in this Github repository: https://github.com/Hydracerynitis/Ethical-Framework
About Kejun: a Bachelor of Advanced Science (Honor) student in the University of Auckland.
Photo of Kejun Dai