Explainable Intelligent Systems
  • Home
  • Team
  • Research
    • Publications
    • Scientific Talks
    • Research-Related Training
    • Public Outreach Events
  • Events
    • Explainable AI and Society
    • Summer School
    • Intelligent Systems in Context
    • Issues in XAI
    • Public Events
  • Press
Select Page

[internal] Iterative Tweaking and the Interpretation of Feature Visualization

by Barnaby Crook | Aug 19, 2021 | Reading Group (internal)

1. Feature Visualization One way to make progress in rendering deep artificial neural networks intelligible is to figure out what is going on inside their hidden layers. ‘Hidden’ in this context just means located between the input and output layers1. Drawing...

Recent Posts

  • Lena visits the IDSIA USI/SUPSI in Lugano April 4, 2022
  • Lena Kästner an die Universität Bayreuth berufen March 3, 2022
  • Blogbeitrag von Eva Schmidt zu Verantwortung für KI-gestütze Entscheidungen December 14, 2021
March 2023
M T W T F S S
 12345
6789101112
13141516171819
20212223242526
2728293031  
« Apr    
  • Facebook
Privacy Policy | Contact | © 2021 Explainable Intelligent Systems