YuanFu Yang

YuanFu Yang

Assistant Professor

Posts by Collection

portfolio

US20150064814

Mechanisms for monitoring ion beam in ion implanter system

TWI534868B

Ion Implantation System and Assembly Thereof and Method for Performing Ion Implantation

publications

The economics of preventive maintenance -A grouping genetic algorithm approach

Published in ICCIE, 2006

As manufactured goods become more complex and customer's expectations grow, increased attention is being paid to maintenance and improving product quality. To avoid the huge losses caused by sudden failures, the present manufacturers of the Hi-Tech industry requires highly reliable and stable equipment. Enterprises have invested more and more resources to maximize machine durability and efficiency in order to maintain good operation of the process flow. After using many resources to improve the tactics of maintenance, the management of the company would like to investigate and assess the present situation of maintenance and the possibility of further improvement. Although a large number of studies have been made on preventive maintenance, little is known about the preventive maintenance planning based on the concept of economics. The main purpose of this study is to construct the Preventive maintenance policies based on Economics. Various treatment methods and maintenance policies are discussed and summarized from the rapidly growing literature. And the model of the economics of preventive maintenance is presented by using the concept of the capital budgeting in this paper. This study proposes a two-step approach. The first step is to propose a function of availability for the singlecomponent and multi-component. And the primary model is constructed based on the grouping genetic algorithm. The second step is to propose an economics perspective of the preventive maintenance model. The single-component and multi-component model are analyzed by the simulation. This study will tell the manager if it is worthwhile to implement the maintenance project or not.

Recommended citation: Yuan-Fu Yang and Yu-Fang David Chiu, "The Economics of Preventive Maintenance - A Grouping Genetic Algorithm Approac", 2006 36th International Conference on Computers and Industrial Engineering (ICCIE), Jan. 2006. https://www.researchgate.net/publication/288315146_The_economics_of_preventive_maintenance_-A_grouping_genetic_algorithm_approach

A Deep Learning Model for Identification of Defect Patterns in Semiconductor Wafer Map

Published in ASMC, 2019

The semiconductors are used as various precision components in many electronic products. Each layer must be inspected of defect after drawing and baking the mask pattern in wafer fabrication. Unfortunately, the defects come from various variations during the semiconductor manufacturing and cause massive losses to the companies' yield. If the defects could be identified and classified correctly, then the root of the fabrication problem can be recognized and eventually resolved. Automatic optical inspection (AOI) is used to visualize defect patterns and identify root causes of die failures. AOI can be replaced a large number of human inspections with high-speed and accurate inspection technology, to achieve consistency in the detection and shorten the inspection time, then improve product quality and competitiveness. The defect is judged from the feature in AOI, but the final goal is to determine if the defect is a true or a pseudo defect of the wafer. Then, we need to determine what defect type is. But the current AOI needs a subsequent final verification by the human to judge the type of defect. Machine learning (ML) techniques have been widely accepted and are well suited for such classification and identification problems. In this paper, we employ convolutional neural networks (CNN) and extreme gradient boosting (XGBoost) for wafer map retrieval tasks and the defect pattern classification. CNN is the most famous deep learning architecture. The recent surge of interest in CNN is due to the immense popularity and effectiveness of convnets. XGBoost is the most popular machine learning framework among data science practitioners, especially on Kaggle, which is a platform for data prediction competitions where researchers post their data and statisticians and data miners compete to produce the best models. CNN and XGBoost are compared with a random decision forests (RF), support vector machine (SVM), adaptive boosting (Adaboost), and the final results indicate a superior classification performance of the proposed method. Our experimental result demonstrates the success of CNN and extreme gradient boosting techniques for the identification of defect patterns in semiconductor wafers. The overall classification accuracy for the test dataset of CNN and extreme gradient boosting is 99.2%/98.1%. We demonstrate the success of this technique for the identification of defect patterns in semiconductor wafers. We believe this is the first time accurate computational classification in such task has been reported achieving accuracy above 99%.

Recommended citation: Yuan-Fu Yang, "A Deep Learning Model for Identification of Defect Patterns in Semiconductor Wafer Map", 2019 30th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Saratoga Springs, NY, USA, 2019, pp. 1-6, doi: 10.1109/ASMC.2019.8791815. https://ieeexplore.ieee.org/abstract/document/8791815

Double Feature Extraction Method for Wafer Map Classification Based on Convolution Neural Network

Published in ASMC, 2020

The individual components of an integrated circuit (IC) are extremely small and its production demands precision at an atomic level. ICs are made by creating circuit structures on a wafer made out of very pure semiconducting material, typically silicon, and interconnecting the structures using wires. In order to produce high density IC, the wafer surface must be extremely clean and the circuit layers fabricated on the previous wafer should be aligned. If these conditions are not satisfied, the high density structure may collapse. To prevent this from happening, the wafers must be constantly cleaned to avoid contamination, and to remove the left-over of the previous process steps. Then, automatic defect classification (ADC) is used to identify and classify wafer surface defects using scanning electron microscope images. However, the classification performance of current ADC systems is poor. If the defects could be classified correctly, then the root of the fabrication problem can be recognized and eventually resolved. Machine learning techniques have been widely accepted and are well suited for such classification problems. In this paper, we propose double feature extraction method based on convolution neural network. The proposed model uses the Radon transform for the first feature extraction, and then input this feature into the convolution layer for the second feature extraction. Experiments with real-world data set verified that the proposed method achieves high defect classification performance, defect pattern recognition accuracy up to 98.5%, and we confirmed the effectiveness of the proposed feature extraction technique.

Recommended citation: Yuan-Fu Yang and Min Sun, "Double Feature Extraction Method for Wafer Map Classification Based on Convolution Neural Network", 2020 31st Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Saratoga Springs, NY, USA, 2020, pp. 1-6, doi: 10.1109/ASMC49169.2020.9185393. https://ieeexplore.ieee.org/abstract/document/9185393

A Novel Deep Learning Architecture for Global Defect Classification: Self-Proliferating Neural Network (SPNet)

Published in ASMC, 2021

The competition in the semiconductor industry is intense, and any manufacturing company's primary concerns are to reduce costs and improve quality and reliability. By increasing the yield and maximizing the throughput of good wafers, lower costs and higher revenues can be achieved. The ability of defect inspection affects the product yield and productivity. The high rate of false negatives in defect inspection will result in defective wafers being treated as normal wafers and shipped to customers. In addition, a high false positives rate will cause non-defective wafers to be considered abnormal and lead to additional review loading by engineers. Therefore, how to reduce both false negatives and false positives is the main challenge for defect inspection. In this paper, we have developed a new deep learning architecture, named Self-Proliferating Neural Network (SPNet). Compared with other methods, SPNet can significantly reduce false positives and false positives, while improving quality and productivity. We also show that our method generalizes well to other public datasets, where they achieve state-of-the-art results. Finally, we apply SPNet to the classification tasks of defect map and defect pattern, and the F1-score achieves 98.9% and 98.2%, respectively. We conduct experiments that probe the robustness of learned representations and conclude that SPNet has significant benefits in robustness and generalization.

Recommended citation: Yuan-Fu Yang and Min Sun, "A Novel Deep Learning Architecture for Global Defect Classification: Self-Proliferating Neural Network (SPNet)", 2021 32nd Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Milpitas, CA, USA, 2021, pp. 1-6, doi: 10.1109/ASMC51741.2021.9714125. https://ieeexplore.ieee.org/abstract/document/9714125

Semiconductor Defect Pattern Classification by Self-Proliferation-and-Attention Neural Network

Published in TSM, 2021

Semiconductor manufacturing is on the cusp of a revolution - the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network (SP&A-Net). This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks.

Recommended citation: Yuan-Fu Yang and Min Sun, "Semiconductor Defect Pattern Classification by Self-Proliferation-and-Attention Neural Network", IEEE Transactions on Semiconductor Manufacturing, vol. 35, no. 1, pp. 16-23, Feb. 2022, doi: 10.1109/TSM.2021.3131597. https://ieeexplore.ieee.org/abstract/document/9628175

Hybrid Quantum-Classical Machine Learning for Lithography Hotspot Detection

Published in ASMC, 2022

In advanced semiconductor process technology, lithography hotspot detection has become an essential task in design for manufacturability. The ability to detect and repair lithography hotspots that can affect printability is critical to improving yield and productivity. Machine learning technology has become a powerful tool in a variety of applications, from finance to manufacturing and computer vision. The use of quantum systems to process classical data using machine learning algorithms has created an emerging field of research, namely quantum machine learning (QML). We explore the possibility of converting a novel machine learning model to a hybrid quantum-classical machine learning that benefits from using variational quantum layers. We show that this hybrid model can perform similar to the classical approach. In addition, we explore parametrized quantum circuits (PQC) with different expressibility and entangling capacities. Then we compare their training performance to quantify the expected benefits. These results can be used to build a future roadmap to develop circuit-based hybrid quantum-classical machine learning for lithography hotspot detection.

Recommended citation: Yuan-Fu Yang and Min Sun, "Hybrid Quantum-Classical Machine Learning for Lithography Hotspot Detection", 2022 33rd Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Saratoga Springs, NY, USA, 2022, pp. 1-6, doi: 10.1109/ASMC54647.2022.9792509. https://ieeexplore.ieee.org/abstract/document/9792509

Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

Published in CVPR, 2022

With the rapid development of artificial intelligence and autonomous driving technology, the demand for semiconductors is projected to rise substantially. However, the massive expansion of semiconductor manufacturing and the development of new technology will bring many defect wafers. If these defect wafers have not been correctly inspected, the ineffective semiconductor processing on these defect wafers will cause additional impact to our environment, such as excessive carbon dioxide emission and energy consumption. In this paper, we utilize the information processing advantages of quantum computing to promote the defect learning defect review (DLDR). We propose a classical-quantum hybrid algorithm for deep learning on near-term quantum processors. By tuning parameters implemented on it, quantum circuit driven by our framework learns a given DLDR task, include of wafer defect map classification, defect pattern classification, and hotspot detection. In addition, we explore parametrized quantum circuits with different expressibility and entangling capacities. These results can be used to build a future roadmap to develop circuit-based quantum deep learning for semiconductor defect detection.

Recommended citation: Yuan-Fu Yang and Min Sun, "Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning", 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 2313-2322, doi: 10.1109/CVPR52688.2022.00236 https://ieeexplore.ieee.org/document/9879978

Medium. Permeation: SARS-COV-2 Painting Creation by Generative Model

Published in arXiv, 2023

Airborne particles are the medium for SARS-CoV-2 to invade the human body. Light also reflects through suspended particles in the air, allowing people to see a colorful world. Impressionism is the most prominent art school that explores the spectrum of color created through color reflection of light. We find similarities of color structure and color stacking in the Impressionist paintings and the illustrations of the novel coronavirus by artists around the world. With computerized data analysis through the main tones, the way of color layout, and the way of color stacking in the paintings of the Impressionists, we train computers to draw the novel coronavirus in an Impressionist style using a Generative Adversarial Network to create our artwork "Medium. Permeation". This artwork is composed of 196 randomly generated viral pictures arranged in a 14 by 14 matrix to form a large-scale painting. In addition, we have developed an extended work: Gradual Change, which is presented as video art. We use Graph Neural Network to present 196 paintings of the new coronavirus to the audience one by one in a gradual manner. In front of LED TV screen, audience will find 196 virus paintings whose colors will change continuously. This large video painting symbolizes that worldwide 196 countries have been invaded by the epidemic, and every nation continuously pops up mutant viruses. The speed of vaccine development cannot keep up with the speed of virus mutation. This is also the first generative art in the world based on the common features and a metaphorical symbiosis between Impressionist art and the novel coronavirus. This work warns us of the unprecedented challenges posed by the SARS-CoV-2, implying that the world should not ignore the invisible enemy who uses air as a medium.

Recommended citation: Yuan-Fu Yang, Iuan-Kai Fang, Min Sun, Su-Chu Hsu, "Medium. Permeation: SARS-COV-2 Painting Creation by Generative Model" arXiv:2304.11354, 2023. https://arxiv.org/abs/2304.11354

A Quantum-Powered Photorealistic Rendering

Published in arXiv, 2023

Achieving photorealistic rendering of real-world scenes poses a significant challenge with diverse applications, including mixed reality and virtual reality. Neural networks, extensively explored in solving differential equations, have previously been introduced as implicit representations for photorealistic rendering. However, achieving realism through traditional computing methods is arduous due to the time-consuming optical ray tracing, as it necessitates extensive numerical integration of color, transparency, and opacity values for each sampling point during the rendering process. In this paper, we introduce Quantum Radiance Fields (QRF), which incorporate quantum circuits, quantum activation functions, and quantum volume rendering to represent scenes implicitly. Our results demonstrate that QRF effectively confronts the computational challenges associated with extensive numerical integration by harnessing the parallelism capabilities of quantum computing. Furthermore, current neural networks struggle with capturing fine signal details and accurately modeling high-frequency information and higher-order derivatives. Quantum computing's higher order of nonlinearity provides a distinct advantage in this context. Consequently, QRF leverages two key strengths of quantum computing: highly non-linear processing and extensive parallelism, making it a potent tool for achieving photorealistic rendering of real-world scenes.

Recommended citation: Yuan-Fu Yang and Min Sun, "QRF: Implicit Neural Representations with Quantum Radiance Fields", arXiv:2211.03418, Nov. 2023. https://arxiv.org/abs/2211.03418

talks

teaching

Computer Vision

Graduate course, Institute of Artificial Intelligence Innovation, NYCU, 2024

Course Overview and Objectives:

This course aims to provide students with a deep understanding of the fundamental concepts and techniques of computer vision, including image formation, feature extraction, 3D reconstruction, image segmentation, object recognition, deep learning, object detection, object tracking, and facial recognition. It also aims to equip students with the implementation and application of algorithms, models, and frameworks related to computer vision, enabling them to address computer vision problems across various domains such as autonomous driving, smart homes, medical image analysis, and more. Through this course, students will comprehend the limitations and challenges of current computer vision applications and explore future development directions. By undertaking this course, students will acquire the following abilities:

  • Fundamental knowledge and skills in computer vision and image processing.
  • Sensitivity and analytical skills toward emerging technologies and trends.
  • Capability to conduct independent research and development, possessing teamwork and project management abilities.
  • Innovative thinking and problem-solving skills, with the capacity to apply learned knowledge to promote technological innovation and societal progress.

Generative AI

Graduate course, Institute of Artificial Intelligence Innovation, NYCU, 2024

Coming Soon!