Authors: Weihong Zhai, Xiupeng Shi, Yiik Diew Wong, Qing Han, Lisheng Chen

Published on: March 19, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2403.12381

Summary

• What is new: A novel explainable automated machine learning technique (xAutoML) for semiconductor yield prediction and improvement.
• Why this is important: Optimizing semiconductor yield rates with reliable diagnosis and prognosis is complex.
• What the research proposes: xAutoML autonomously learns optimal models for yield prediction with explainability and key diagnosis insights.
• Results: xAutoML shows superior performance in yield improvement and defect diagnosis with adaptive optimization and explainability.

Technical Details

Technological frameworks used: xAutoML

Models used: Optimized classifiers with adaptive loss

Data used: Semiconductor manufacturing data

Potential Impact

Semiconductor manufacturing and smart manufacturing sectors

Want to implement this idea in a business?

We have generated a startup concept here: OptiYield.