Xiaohong Ma

Papers

Total Citations

H-Index

About

Xiaohong Ma is a researcher at the forefront of visual analytics and machine learning interpretability. Her primary research focuses on developing intuitive visual analysis approaches that bridge the gap between complex machine learning models and human understanding. Ma’s most notable contribution is the creation of EasySVM, a pioneering visual analysis framework for open-box support vector machines, which allows users to interactively explore and understand the inner workings of SVM classifiers. This work, published in 2017, has garnered 41 citations, reflecting its significant impact on making advanced machine learning techniques more accessible to researchers and practitioners. By enabling transparent model inspection, Ma’s research empowers users to validate, debug, and trust their models, a crucial step toward responsible AI. Her work stands out for its practical application in demystifying black-box algorithms, making her a key figure in the growing field of explainable artificial intelligence.