Measurement of Explanations Generated by XAI Methods Using Features.

Journal: Studies in health technology and informatics
Published Date:

Abstract

An increasing number of explainability methods began to emerge as a response for the black-box methods used to make decisions that could not be easily explained. This created the need for a better evaluation for these methods. In this paper we propose a new method for evaluation based on features. The main advantage of applying the proposed method to CNNs explanations are: a fully automated way to measure the quality of an explanation and the fact that the score uses the same information as the CNN, in this way being able to offer a measure of the quality of explanation that can be obtained automatically, ensuring that the human bias will not be present in the measurement of the explanation.

Authors

  • Cătălin-Mihai Pesecan
    Politehnica University of Timişoara, Timişoara, Romania.
  • Lăcrămioara Stoicu-Tivadar
    Faculty of Automatics and Computers, University Politehnica Timişoara, Romania.