Presented By O'Reilly and Cloudera
Make Data Work
Feb 17–20, 2015 • San Jose, CA

Interpretable Machine Learning in Practice

Maya Gupta (Google)
11:00am–11:30am Wednesday, 02/18/2015
Hardcore Data Science
Location: LL20 BC.
Average rating: ****.
(4.67, 3 ratings)

What makes a large machine learning system more interpretable and robust in practice? How do we take into account engineer’s prior information about signals? We’ll discuss the importance of monotonicity, smoothness, semantically-meaningful inputs and outputs, and designing algorithms that are easy to debug.

Photo of Maya Gupta

Maya Gupta


Gupta runs an R&D group at Google Research focused on designing efficient and transparent statistical learning algorithms. From 2003-2012, she was a professor of electrical engineering at the Univ. of Washington. Gupta received the PECASE award in 2007 from Pres. George Bush, and the ONR YIP award in 2007. She completed the PhD from Stanford EE in 2003 as an NSF Fellow, working with Bob Gray and Richard Olshen. Gupta holds a BS EE and BA Econ at Rice University, 1997. Gupta was a color image processing researcher from 2000-2003 at Ricoh’s California Research Center, and has also worked for AT&T Labs, Microsoft, NATO, and HP, and is the Founder and CEO of Artifact Puzzles.

Comments on this page are now closed.


Ahmed Soliman
02/18/2015 3:30am PST

Can you please share the talk slides?