Ruth Fong
Research
Interests: computer vision, machine learning, deep learning, explainable AI
Short Bio
Ruth Fong joined the department as a teaching faculty member in 2021, after earning her Ph.D. in engineering science from the University of Oxford, where she also received a master's. She completed her bachelor's in computer science at Harvard University. Her research interests include computer vision, machine learning, deep learning, and explainable AI. In addition to teaching introductory courses, she conducts research focused on developing novel techniques for understanding AI models after training, designing new AI models that are interpretable by design, and introducing paradigms for finding and correcting existing failure points in AI models. She received a Rhodes Scholarship in 2015 and an Open Philanthropy AI Fellowship in 2018.
Selected Publications
- Iro Laina, Ruth C. Fong, and Andrea Vedaldi, NeurIPS 2020. "Quantifying learnability and describability of visual concepts emerging in representation learning."
- Ruth Fong*, Mandela Patrick*, and Andrea Vedaldi, ICCV 2019. "Understanding deep networks via extremal perturbations and smooth masks."
- Ruth Fong and Andrea Vedaldi, CVPR 2018. "Net2Vec: Quantifying and explaining how concepts are encoded by filters in deep neural networks."
- Ruth C. Fong, Walter J. Scheirer, and David D. Cox, Scientific Reports 2018. "Using human brain activity to guide machine learning."
- Ruth C. Fong and Andrea Vedaldi, ICCV 2017. "Interpretable explanations of black boxes by meaningful perturbation."
