Explainable AI for domain experts: a post Hoc analysis of deep learning for defect classification of TFT–LCD panels

Minyoung Lee, Joohyoung Jeon, Hongchul Lee

Research output: Contribution to journalArticlepeer-review

Abstract

The deep learning (DL) model has performed successfully in various fields, including manufacturing. DL models for defect image data analysis in the manufacturing field have been applied to multiple domains such as defect detection, classification, and localization. However, DL models require trade-offs in accuracy and interpretability. We use explainable artificial intelligence techniques to analyze the predicted results of the defect image classification model, which is considered as a “black-box” model, to produce human-understandable results. We visualize defects using layer-wise relevance propagation-based methods, fit the model into a decision tree, and convert prediction results into human-interpretable text. Our research complements the interpretation of prediction results for the classification model. The domain expert can obtain the reliability and explanatory ability for the defect classification of TFT–LCD panel data of the DL model through the results of the proposed analysis.

Original languageEnglish
JournalJournal of Intelligent Manufacturing
DOIs
Publication statusAccepted/In press - 2021

Keywords

  • Deep learning
  • Defect classification
  • Explainable artificial intelligence
  • Visualization

ASJC Scopus subject areas

  • Software
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Explainable AI for domain experts: a post Hoc analysis of deep learning for defect classification of TFT–LCD panels'. Together they form a unique fingerprint.

Cite this