AIの説明可能性


本資料は2020年07月11日に社内共有資料として展開していたものを WEBページ向けにリニューアルした内容になります。



■Contents

 

●Concept/Motivation


●Recent trends on XAI


●Method 1: LIME/SHAP

  • Example: Classification

  • Example: Regression

  • Example: Image classification


●Method 2: ABN for image classification



■Concept/Motivation

 

Generally speaking, AI is a blackbox.

We want AI to be explainable because…

1. Users should trust AI to actually use it (prediction itself, or model)

Ex: diagnosis/medical check, credit screening

G. Tolomei, et. al., arXiv:1706.06691


People want to know why they were rejected by AI screening, and what they should do in order to pass the screening.



2. It helps to choose a model from some candidates

Classifier of text to “Christianity” or “Atheism” (無神論)

Both model give correct classification, but it is apparent that model 1 is better than model 2.