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