Dan Scarafoni is a PhD candidate, co-advised by Thomas Ploetz and Irfan Essa. He joined the team in 2018, after working as a deep learning and HCI researcher at MIT for several years. His research interests include interpretability of machine learning, with particular emphasis on deep learning technologies. He holds a B.S. and M.S. in computer science from University of Rochester. His undergraduate thesis was supervised by Professor Lenhart Schubert, and his Master’s research and thesis was supervised by Philip Guo (now at UCSD) and Eshan Hoque.

Dan’s research focuses on novel applied human activity recognition and skill assessment techniques from synthesized classifier inputs, and finding novel abstractions for human activity recognition. His current work focuses on augmenting activity recognition with skill assessment techniques, and vice versa

The most up to date information of his research can be found at his website:

www.scarafoni.com

CV, Publications, and Presentations