AI-Driven Wafer Inspection: Deep Learning, Transformers, and Generative Models for Defect Analysis in Semiconductor Manufacturing | Chapter 10 | Mathematics and Computer Science: Research Updates Vol. 8

 

Semiconductor manufacturing at advanced technology nodes demands inspection systems capable of identifying increasingly subtle, stochastic, and mixed-type defects. Traditional rule-based and handcrafted-feature approaches are no longer sufficient to address the complexity of modern wafer patterns, prompting the integration of artificial intelligence (AI) into high-volume manufacturing workflows. This chapter presents a unified framework for AI-driven wafer inspection that combines convolutional neural networks (CNNs), Vision Transformers (ViTs), and generative models such as variational autoencoders (VAEs) and generative adversarial networks (GANs). CNNs are effective for wafer map pattern classification, learning hierarchical spatial features that capture centre, edge-ring, and composite wafer failure modes. Transformers extend this capability by modelling long-range spatial dependencies, enabling improved performance in optical and SEM imaging scenarios where global context is essential. Generative models enhance sensitivity to rare or previously unseen defects by learning the underlying distribution of defect-free patterns and detecting deviations through reconstruction error or anomaly scoring.

 

 

 

A hybrid ViT–GAN architecture is introduced to demonstrate how discriminative and generative pathways can be fused to deliver high accuracy and low false-alarm rates across diverse defect classes. Extensive comparisons using public datasets and synthetic SEM-like datasets show that AI models substantially outperform classical techniques, particularly in low-sample regimes and in the presence of noise, illumination variations, or rotation. Deployment considerations, including inference speed, model compression, domain adaptation, and explainability, are discussed to highlight practical challenges in integrating AI into semiconductor fabs. The chapter concludes with emerging trends such as self-supervised learning, large vision models, multimodal data fusion, and temporal defect modelling, which are expected to shape the next generation of intelligent wafer inspection systems.

 

 

Author(s) Details

Balachandar Jeganathan
ASML, San Jose, CA, USA.

 

Please see the book here :- https://doi.org/10.9734/bpi/mcsru/v8/6853

 

A Review of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) Systems, and Convolutional Neural Networks (CNNs) in Application Systems | Chapter 8 | Science and Technology: Developments and Applications Vol. 5

The rapid development of artificial intelligence (AI) has brought disruptive changes across many industries, with large language models (LLMs), Retrieval-Augmented Generation (RAG) systems, and convolutional neural networks (CNNs) featured prominently in this massive transformation. The advent of Artificial Intelligence (AI) in recent years has transformed the technology landscape like never before. More implementations of AI-powered applications have led to advanced and sophisticated supporting technologies such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) systems, and Convolutional Neural Networks (CNNs). Application systems using these advanced technologies are transforming businesses across industries. LLM enhances natural language understanding and also aids in generation, facilitating communications closely resembling human interactions. RAG systems integrate retrieval mechanisms with generative capabilities, improving the relevance and accuracy of generated content by leveraging external knowledge bases. Meanwhile, CNNs continue to excel in image processing tasks, driving advancements in computer vision applications. The collective synergies between these technologies help businesses in improving efficiency, user experience, and decision-making.

The study illustrates implementations while revealing the challenges and opportunities presented by these technologies. The research on these technologies underscores the necessity for ongoing research and adaptation in leveraging these technologies to maximize their potential in real-world applications.

The study concluded that the technologies of LLMs, RAG, and CNNs have a far-reaching and disruptive effect on application systems, impacting many industries. LLMs are reshaping the landscape of natural language processing, allowing for more nuanced systems that comprehend, produce, and communicate human language.

 

Author (s) Details

 

Balagopal Ramdurai
IEEE, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/stda/v5/4045