Manipulating and Measuring Model Interpretability

    arXiv: Artificial Intelligence, Volume abs/1802.07810, 2018.

    Cited by: 120|Bibtex|Views46|Links
    EI

    Abstract:

    Despite a growing body of research focused on creating interpretable machine learning methods, there have been few empirical studies verifying whether interpretable methods achieve their intended effects on end users. We present a framework for assessing the effects of model interpretability on users via pre-registered experiments in whic...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments