A new technical paper titled “An Evaluation of Continual Learning for Advanced Node Semiconductor Defect Inspection” was published by Imec and SCREEN SPE Germany.

Abstract

“Deep learning-based semiconductor defect inspection has gained traction in recent years, offering a powerful and versatile approach that provides high accuracy, adaptability, and efficiency in detecting and classifying nano-scale defects. However, semiconductor manufacturing processes are continually evolving, leading to the emergence of new types of defects over time. This presents a significant challenge for conventional supervised defect detectors, as they may suffer from catastrophic forgetting when trained on new defect datasets, potentially compromising performance on previously learned tasks. An alternative approach involves the constant storage of previously trained datasets alongside pre-trained model versions, which can be utilized for (re-)training from scratch or fine-tuning whenever encountering a new defect dataset. However, adhering to such a storage template is impractical in terms of size, particularly when considering High-Volume Manufacturing (HVM). Additionally, semiconductor defect datasets, especially those encompassing stochastic defects, are often limited and expensive to obtain, thus lacking sufficient representation of the entire universal set of defectivity. This work introduces a task-agnostic, meta-learning approach aimed at addressing this challenge, which enables the incremental addition of new defect classes and scales to create a more robust and generalized model for semiconductor defect inspection. We have benchmarked our approach using real resist-wafer SEM (Scanning Electron Microscopy) datasets for two process steps, ADI and AEI, demonstrating its superior performance compared to conventional supervised training methods.”

Find the technical paper here.  Published July 2024 (preprint).

Prasad, Amit, Bappaditya Dey, Victor Blanco, and Sandip Halder. “An Evaluation of Continual Learning for Advanced Node Semiconductor Defect Inspection.” arXiv preprint arXiv:2407.12724 (2024).

The post Classification and Localization of Semiconductor Defect Classes in Aggressive Pitches (imec, Screen) appeared first on Semiconductor Engineering.

A new technical paper titled “An Evaluation of Continual Learning for Advanced Node Semiconductor Defect Inspection” was published by Imec and SCREEN SPE Germany.

Abstract

“Deep learning-based semiconductor defect inspection has gained traction in recent years, offering a powerful and versatile approach that provides high accuracy, adaptability, and efficiency in detecting and classifying nano-scale defects. However, semiconductor manufacturing processes are continually evolving, leading to the emergence of new types of defects over time. This presents a significant challenge for conventional supervised defect detectors, as they may suffer from catastrophic forgetting when trained on new defect datasets, potentially compromising performance on previously learned tasks. An alternative approach involves the constant storage of previously trained datasets alongside pre-trained model versions, which can be utilized for (re-)training from scratch or fine-tuning whenever encountering a new defect dataset. However, adhering to such a storage template is impractical in terms of size, particularly when considering High-Volume Manufacturing (HVM). Additionally, semiconductor defect datasets, especially those encompassing stochastic defects, are often limited and expensive to obtain, thus lacking sufficient representation of the entire universal set of defectivity. This work introduces a task-agnostic, meta-learning approach aimed at addressing this challenge, which enables the incremental addition of new defect classes and scales to create a more robust and generalized model for semiconductor defect inspection. We have benchmarked our approach using real resist-wafer SEM (Scanning Electron Microscopy) datasets for two process steps, ADI and AEI, demonstrating its superior performance compared to conventional supervised training methods.”

Find the technical paper here.  Published July 2024 (preprint).

Prasad, Amit, Bappaditya Dey, Victor Blanco, and Sandip Halder. “An Evaluation of Continual Learning for Advanced Node Semiconductor Defect Inspection.” arXiv preprint arXiv:2407.12724 (2024).

The post Classification and Localization of Semiconductor Defect Classes in Aggressive Pitches (imec, Screen) appeared first on Semiconductor Engineering.

A technical paper titled “Metrology for 2D materials: a perspective review from the international roadmap for devices and systems” was published by researchers at Arizona State University, IBM Research, Unity-SC, and the National Institute of Standards and Technology (NIST).

Abstract:

“The International Roadmap for Devices and Systems (IRDS) predicts the integration of 2D materials into high-volume manufacturing as channel materials within the next decade, primarily in ultra-scaled and low-power devices. While their widespread adoption in advanced chip manufacturing is evolving, the need for diverse characterization methods is clear. This is necessary to assess structural, electrical, compositional, and mechanical properties to control and optimize 2D materials in mass-produced devices. Although the lab-to-fab transition remains nascent and a universal metrology solution is yet to emerge, rapid community progress underscores the potential for significant advancements. This paper reviews current measurement capabilities, identifies gaps in essential metrology for CMOS-compatible 2D materials, and explores fundamental measurement science limitations when applying these techniques in high-volume semiconductor manufacturing.”

Find the technical paper here. Published April 2024.

Changming Wu et al., Freeform direct-write and rewritable photonic integrated circuits in phase-change thin films.Sci. Adv.10,eadk1361(2024).DOI:10.1126/sciadv.adk1361

Further Reading
Closing The Test And Metrology Gap In 3D-IC Packages
Finding defects in stacked die is a daunting challenge. Equipment, processes, and methodologies all need modifications, and that’s just for starters.
Pressure Builds On Failure Analysis Labs
Goal is to find the causes of failures faster and much earlier — preferably before first silicon.

The post Metrology For 2D Materials: A Review From The International Roadmap For Devices And Systems (NIST, Et Al.) appeared first on Semiconductor Engineering.