首页|Massachusetts Institute of Technology Researcher Yields New Study Findings on Ma chine Learning (Multi-Objective Framework to Balancing Fairness and Accuracy for Debiasing Machine Learning Models)
Massachusetts Institute of Technology Researcher Yields New Study Findings on Ma chine Learning (Multi-Objective Framework to Balancing Fairness and Accuracy for Debiasing Machine Learning Models)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news originating from Cambridge, Ma ssachusetts, by NewsRx editors, the research stated, "Machine learning algorithm s significantly impact decision-making in high-stakes domains, necessitating a b alance between fairness and accuracy." Funders for this research include Machine Learning Applications Consortium of Mi t Csail; Future of Data Consortium. Our news correspondents obtained a quote from the research from Massachusetts In stitute of Technology: "This study introduces an in-processing, multi-objective framework that leverages the Reject Option Classification (ROC) algorithm to sim ultaneously optimize fairness and accuracy while safeguarding protected attribut es such as age and gender. Our approach seeks a multi-objective optimization sol ution that balances accuracy, group fairness loss, and individual fairness loss. The framework integrates fairness objectives without relying on a weighted summ ation method, instead focusing on directly optimizing the trade-offs."
Massachusetts Institute of TechnologyC ambridgeMassachusettsUnited StatesNorth and Central AmericaCyborgsEmer ging TechnologiesMachine Learning
NETL
NSTL
