YoVDO

WheaCha: An Explanation Method for Models of Code

Offered By: ACM SIGPLAN via YouTube

Tags

Explainable AI Courses Machine Learning Courses Software Engineering Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a groundbreaking explanation method for code models in this 17-minute conference talk from OOPSLA2 2023. Discover WheaCha, a novel approach that separates input programs into 'wheat' (defining features) and 'chaff' to explain model predictions. Learn how the HuoYan tool implements WheaCha to explain four prominent code models: code2vec, seq-GNN, GGNN, and CodeBERT. Examine the efficiency of HuoYan, taking less than twenty seconds on average to compute wheat for an input program. Understand how the wheat used by models for predictions primarily consists of simple syntactic or lexical properties. Compare WheaCha's effectiveness to other explainability methods like SIVAND, CounterFactual Explanations, Integrated Gradients, and SHAP. Explore the practical applications of WheaCha in helping users identify defective code models trained on mislabeled or biased data. Gain insights into the latest advancements in explainable AI for code models and their potential impact on software development and analysis.

Syllabus

[OOPSLA23] An Explanation Method for Models of Code


Taught by

ACM SIGPLAN

Related Courses

Explainable AI: Scene Classification and GradCam Visualization
Coursera Project Network via Coursera
Artificial Intelligence Privacy and Convenience
LearnQuest via Coursera
Natural Language Processing and Capstone Assignment
University of California, Irvine via Coursera
Modern Artificial Intelligence Masterclass: Build 6 Projects
Udemy
Data Science for Business
DataCamp