Information entropy measures for evaluation of reliability of deep neural network results

HIGHLIGHTS

  • who: Elakkat D. Gireesh and Varadaraj P. Gurupur from the Department of Computer Engineering, University of Central Florida, Orlando, FL, USA have published the Article: Information Entropy Measures for Evaluation of Reliability of Deep Neural Network Results, in the Journal: Entropy 2023, 573 of 27/03/2023
  • what: The authors demonstrate that the robustness of the relationship between certainty index with the sample entropy demonstrated through sample entropy-heatmap correlation is higher than that with the original signal indicating that the DNN focuses on information rich regions of the signal to arrive at decisions. Keeping . . .

     

    Logo ScioWire Beta black

    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.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?