Explainable AI for Software Engineering

Explainable AI for Software Engineering

Hands-on Exercise

ASE2021 PyExplainer Live-Demo
ASE2021 Hands-on Exercise

Part1-What is Explainable AI?

A Theory of Explanations
Techniques for Generating Explanations
Model-specific Techniques for Generating Global Explanations
Model-agnostic Techniques for Generating Local Explanations

Part2-Defect Prediction Models

Software Quality Assurance
Defect Prediction
(Step 1) Data Collection
(Step 2) Data Preprocessing
(Step 3) Model Construction
(Step 4) Model Evaluation
(Step 5) Model Ranking

Part3-Explainable AI for Software Engineering

Explainability in Software Engineering
A Case Study of Defect Prediction
(Example 1) Help developers localize which lines of code are the most risky
(Example 2) Help developers understand why a file is predicted as defective
(Example 3) Help managers develop software quality improvement plans

Powered by Jupyter Book

Index

By Chakkrit Tantithamthavorn and Jirayus Jiarpakdee
© Copyright 2021.

This project has received funding from the Australian Research Council's Discovery Early Career Researcher Award (ARC DECRA) funding scheme (DE200100941). This book reflects the views of the authors and neither Australian Research Council nor Monash University are liable for any use that may be made of the information contained herein. The content of this project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. The source code that is part of the content, as well as the source code used to format and display that content is licensed under the MIT License.