I am interested in designing high-performance machine learning methods that make sense to humans. Here is a short writeup about why I care.
My focus is building interpretability method for already-trained models (e.g., high performance neural networks). In particular, I believe the language of explanations should include higher-level, human-friendly concepts.
Previously, I built interpretable latent variable models (featured at Talking Machines, and MIT news) and creating structured Bayesian models of human decisions. I have applied these ideas to data from various domains: computer programming education, autism spectrum discorder data, recipes, disease data, 15 years of crime data from the city of Cambridge, human dialogue data from the AMI meeting corpus, and text-based chat data during disaster response. I graduated with a PhD from CSAIL, MIT.
I gave a tutorial at CVPR 2018 (slides) and gave a tutorial on Interpretable machine learning at ICML 2017, slides are here and video is here .
My work was featured in an episode in Talking Machine (which I have not had courage to listen myself talking). Many thanks for Katherine Gorman!
Other stuff I help with:
Co-organizer 3rd ICML 2018 Worshop on Human Interpretability in Machine Learning (WHI),
Workshop Chair at ICLR 2018
Senior program committee at AISTATS 2018
Area chair and program chair at NIPS 2017 and 2018
Steering committee and area chair at FAT* conference
Program committee at ICML 2017/2018, AAAI 2017, IJCAI 2016 (and many other conference before that...)
Executive board member of Women in Machine Learning.
Co-organizer 1st ICML 2016 Worshop on Human Interpretability in Machine Learning (WHI),
2nd ICML 2017 Worshop on Human Interpretability in Machine Learning (WHI).
and NIPS 2016 Worshop on Interpretable Machine Learning for Complex Systems.
Google Scholar
