HIGHLIGHTS
SUMMARY
An increasingly diverse set of methods has been recently proposed and broadly classified as part of IML. Others, meanwhile, discuss how common IML methods can fail to help humans in the real world, both through pointing out hidden assumptions and dangers as well as conducting case studies with users. This article embraces the seeming shortcomings of IML methods as providing merely "facts"15 or "summary statistics"21 about a model, and instead focuses on the practical questions of when and how these methods can be useful. In general, you should expect that a method . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.