Semiconductor Manufacturing

Semiconductor manufacturing research intensely focuses on improving efficiency, yield, and defect detection through advanced data analysis and automation. Current efforts leverage machine learning, particularly deep learning architectures like convolutional neural networks, graph neural networks, and transformers, alongside techniques such as reinforcement learning and tensor-based methods, to model complex processes, predict device performance, and optimize manufacturing steps. These advancements aim to address challenges like process variations, nano-scale defect analysis, and efficient resource allocation, ultimately leading to faster, cheaper, and higher-quality semiconductor production. The resulting improvements in predictive modeling and process control have significant implications for the entire electronics industry.

Papers

September 30, 2022

Experts in the Loop: Conditional Variable Selection for Accelerating Post-Silicon Analysis Based on Deep Learning
Yiwen Liao, Raphaël Latty, Bin Yang
Deep Learning Expert Knowledge Variable Selection Semiconductor Manufacturing Conditional Variable Selection

March 7, 2022

On the Construction of Distribution-Free Prediction Intervals for an Image Regression Problem in Semiconductor Manufacturing
Inimfon I. Akpabio, Serap A. Savari
Construction Industry Quantile Regression Semiconductor Manufacturing Image Regression

February 21, 2022

AI/ML Algorithms and Applications in VLSI Design and Technology
Deepthi Amuru, Harsha V. Vudumula, Pavan K. Cherupally, Sushanth R. Gurram, Amir Ahmad, Andleeb Zahra, Zia Abbas
Machine Learning Artificial Intelligence Financial Application Machine Learning Algorithm Technology Information Data Semiconductor Manufacturing Large Scale Integration

February 7, 2022

Automatic defect segmentation by unsupervised anomaly learning
Nati Ofir, Ran Yacobi, Omer Granoviter, Boris Levant, Ore Shtalrid
Unsupervised Anomaly Detection U Shaped Network Semiconductor Manufacturing Defect Segmentation

December 5, 2021

Using Convolutional Neural Networks for fault analysis and alleviation in accelerator systems
Jashanpreet Singh Sraw, Deepak M C
Convolutional Neural Network Real Time Fault Detection Semiconductor Manufacturing AID User System Reliability Accelerator Tuning

Semiconductor Manufacturing

Papers

Experts in the Loop: Conditional Variable Selection for Accelerating Post-Silicon Analysis Based on Deep Learning

On the Construction of Distribution-Free Prediction Intervals for an Image Regression Problem in Semiconductor Manufacturing

AI/ML Algorithms and Applications in VLSI Design and Technology

Automatic defect segmentation by unsupervised anomaly learning

Using Convolutional Neural Networks for fault analysis and alleviation in accelerator systems