Expert-Informed, User-Centric Explanations for Image Classification with Deep Learning

Expert-Informed, User-Centric Explanations for Image Classification with Deep Learning

USC Information Sciences Institute via YouTube Direct link

Welcome to the Al Seminar Series

1 of 24

1 of 24

Welcome to the Al Seminar Series

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Expert-Informed, User-Centric Explanations for Image Classification with Deep Learning

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Welcome to the Al Seminar Series
  2. 2 Overview
  3. 3 Background: Learning to Classify images with Convolution Neural Networks
  4. 4 Background XAI
  5. 5 XAI tools have proved useful for identifying when a decisi based on irrelevant information.
  6. 6 XAI vs Expert Explanations
  7. 7 What's the role of an explanation?
  8. 8 Pneumonia Detection
  9. 9 Deep Learners find one sufficient means of disting
  10. 10 Center of Mass for explanations
  11. 11 Variability on Explanations can be reduced by ensembles of classifiers and averaging heatmaps
  12. 12 Averaging Multiple Explanations
  13. 13 Data Sets
  14. 14 Experimental setup
  15. 15 Evaluation on Experienced Birdwatchers
  16. 16 Would you trust a robot to identify and remove cancerous moles?
  17. 17 Comments on XAI
  18. 18 Diagnostic Features: Melanomia
  19. 19 Do experienced birders prefer arrows labeled with diagnostic features
  20. 20 Do Novices Learn faster when given diagnostic fea
  21. 21 Learning to label with diagnostic/explanatory fae
  22. 22 Multi-task learning for classification and diagnostic features
  23. 23 Putting it all together
  24. 24 Papers

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.