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

Yang, Yuan-Fu; Sun, Min

doi:10.1109/asmc51741.2021.9714125

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Even in semiconductor manufacturing, sophisticated and intricate industries, ML methods can still be used for them. This includes using optimized model architectures based on traditional ML models 2 or innovative ones, 3 and improved optimization algorithms 4 in yield prediction and analysis, manufacturing process excursion detection, and manufacturing flow simplification. 5 In model architectures, most current models are designed mainly by human experts, which is very time-consuming due to the need for sufficient domain knowledge and trial and error for suitable architectures.…”

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neuroevolution-Based Network Architecture Evolution in Semiconductor Manufacturing

2023

View full text Add to dashboard Cite

Promoted model architectures or algorithms are crucial for intelligent manufacturing since developing them takes a lot of trial and error to embed the domain knowledge into the models correctly. Especially in semiconductor manufacturing, the whole processes depend on complicated physical equations and sophisticated fine-tuning. Therefore, we use a neuroevolution-based model to search the optimized architecture automatically. The collector current value at a particular bias of the silicon–germanium (SiGe) heterojunction bipolar transistor, generated by technology computer-aided design (TCAD), is used as the target dataset with six process parameters as the inputs. The processes include oxidation, dry and wet etching, implantation, annealing, diffusion, and chemical–mechanical polishing. Our work can build a suitable model network with a fast turnaround time, and practical physical constraints are fused in it without domain knowledge extraction. Take the case with 3840 data and one output as an instance. The mean square errors of the train set and validation set, as well as the mean absolute percentage error of the test set, are 1.317 × 10–6, 7.215 × 10–7, and 0.216 while using multilayer perceptron (MLP) and they are 3.285 × 10–7, 1.661 × 10–7, and 0.097 while using NE. The consequences show that the work in this vein is promising. According to the trend plot and results, the ability to extract physic is much better than the traditional (MLP) model.

show abstract

Section: ■ Introductionmentioning

confidence: 99%