Machine-Learning-Based Identification of Defect Patterns in Semiconductor Wafer Maps: An Overview and Proposal

Comparison of Knowledge Acquisition Methods for Dynamic Scheduling of Wafer Test Processes with Unpredictable Testing Errors

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2015.p0058 ◽

2015 ◽

Vol 19 (1) ◽

pp. 58-66

Author(s):

Tsubasa Matsuo ◽

◽

Masahiro Inuiguchi ◽

Kenichiro Masunaga ◽

Keyword(s):

Machine Learning ◽

Project Scheduling ◽

Dynamic Scheduling ◽

Scheduling Problem ◽

Learning Approaches ◽

Dispatching Rule ◽

Semiconductor Wafer ◽

Project Scheduling Problem ◽

Wafer Test ◽

Knowledge Acquisition Methods

The scheduling of semiconductor wafer testing processes may be seen as a resource constraint project scheduling problem (RCPSP), but it includes uncertainties caused by wafer error, human factors, etc. Because uncertainties are not simply quantitative, estimating the range of the parameters is not useful. Considering such uncertainties, finding a good situationdependent dispatching rule is more suitable than solving an RCPSP under uncertainties. In this paper we apply machine learning approaches to acquiring situation-dependent dispatching rule. We compare obtained rules and examine their effectiveness and usefulness in problems with unpredictable wafer testing errors.

Download Full-text

Inspection and Classification of Semiconductor Wafer Surface Defects Using CNN Deep Learning Networks

Applied Sciences ◽

10.3390/app10155340 ◽

2020 ◽

Vol 10 (15) ◽

pp. 5340

Author(s):

Jong-Chih Chien ◽

Ming-Tao Wu ◽

Jiann-Der Lee

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Surface Defects ◽

Semiconductor Industry ◽

Superior Performance ◽

Wafer Surface ◽

Learning Networks ◽

Semiconductor Wafer ◽

Processing Technologies

Due to advances in semiconductor processing technologies, each slice of a semiconductor is becoming denser and more complex, which can increase the number of surface defects. These defects should be caught early and correctly classified in order help identify the causes of these defects in the process and eventually help to improve the yield. In today’s semiconductor industry, visible surface defects are still being inspected manually, which may result in erroneous classification when the inspectors become tired or lose objectivity. This paper presents a vision-based machine-learning-based method to classify visible surface defects on semiconductor wafers. The proposed method uses deep learning convolutional neural networks to identify and classify four types of surface defects: center, local, random, and scrape. Experiments were performed to determine its accuracy. The experimental results showed that this method alone, without additional refinement, could reach a top accuracy in the range of 98% to 99%. Its performance in wafer-defect classification shows superior performance compared to other machine-learning methods investigated in the experiments.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text