The trick to accurate interpretability is to decouple accuracy from explanations.
Just like an International Master commentator can explain most of the moves of a Super GM, so can an interpretable simple model explain the predictions of a very complex black box model.
The work by Caruana referenced in this article actually culminated in a method to get both very accurate models and still retain interpretability.
Just like an International Master commentator can explain most of the moves of a Super GM, so can an interpretable simple model explain the predictions of a very complex black box model.
The work by Caruana referenced in this article actually culminated in a method to get both very accurate models and still retain interpretability.
https://vimeo.com/125940125
http://www.cs.cornell.edu/~yinlou/projects/gam/
More recently there was LIME:
https://homes.cs.washington.edu/~marcotcr/blog/lime/
And there are workshops:
http://www.blackboxworkshop.org/pdf/Turner2015_MES.pdf
We will get there. 'Permanent' is a very long time and in the grand scale of things, deep learning is relatively new.