Goto

Collaborating Authors

 generative counterfactual introspection

Generative Counterfactual Introspection for Explainable Deep Learning

Liu, Shusen, Kailkhura, Bhavya, Loveland, Donald, Han, Yong

arXiv.org Artificial Intelligence

In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental interventional operation that allows us to obtain answers to counterfactual inquiries, i.e., what meaningful change can be made to the input image in order to alter the prediction. We demonstrate how to reveal interesting properties of the given classifiers by utilizing the proposed introspection approach on both the MNIST and the CelebA dataset.

  artificial intelligence, generative counterfactual introspection, machine learning, (15 more...)
1907.03077
  Country:
  Genre: Research Report (0.82)
  Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)

Add feedback