In my last two posts, I wrote about model interpretability, with the goal of trying to understanding what it means and how to measure it. In the first post, I described the disconnect between our mental models and algorithmic models, and how interpretability could potentially reduce it. In the second post, I laid out four things that a model interpretation should allow us to do – mitigate bias, account for context, extract knowledge and generalize. In this post, I want to discuss a number of desirable properties that have been suggested for model interpretations, and that might be used to judge whether and how much a model or explanation is interpretable.
-
Recent Posts
Recent Comments
RNN classification w… on Rolling and Unrolling RNN… Practical Considerat… on K-modes Yajun Liu on Intrinsic vs. Extrinsic S… Important DS AI ML A… on K-modes Beyond PLM (Product… on Graphs and networks Archives
- December 2016
- November 2016
- October 2016
- June 2016
- April 2016
- January 2016
- November 2015
- October 2015
- July 2015
- June 2015
- May 2015
- January 2015
- September 2014
- June 2014
- May 2014
- March 2014
- February 2014
- January 2014
- December 2013
- October 2013
- September 2013
- August 2013
- July 2013
- June 2013
- May 2013
- April 2013
- March 2013
Categories
Meta