Simulator acceleration and inverse design of fin field-effect transistors using machine learning

Kim, In-Soo; Park, So Jeong; Jeong, Changwook; Shim, Mun‐Bo; Kim, Dae Sin; Kim, Gyu-Tae; Seok, Junhee

doi:10.1038/s41598-022-05111-3

Cited by 16 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On one hand, the 2D materials could be an enabler for constructing devices for AI, such as memristors, photodetectors, etc. [118][119][120][121][122] . On the other hand, AI tools such as machine and deep learning can not only accelerate the discovery, design and optimization of 2D materials [123][124][125][126] , but also can interpret the signals generated by sensors based on 2D materials.…”

Section: The Meta-verse Of Composites Manufacturingmentioning

confidence: 99%

Graphene nanoparticles as data generating digital materials in industry 4.0

Ali

Irfan

Khan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

One of the potential applications of 2D materials is to enhance multi-functionality of structures and components used in aerospace, automotive, civil and defense industries. These multi-functional attributes include sensing, energy storage, EMI shielding and property enhancement. In this article, we have explored the potential of using graphene and its variants as data generating sensory elements in Industry 4.0. We have presented a complete roadmap to cover three emerging technologies i.e. advance materials, artificial intelligence and block-chain technology. The utility of 2D materials such as graphene nanoparticles is yet to be explored as an interface for digitalization of a modern smart factory i.e. “factory-of-the-future”. In this article, we have explored how 2D material enhanced composites can act as an interface between physical and cyber spaces. An overview of employing graphene-based smart embedded sensors at various stages of composites manufacturing processes and their application in real-time structural health monitoring is presented. The technical challenges associated with interfacing graphene-based sensing networks with digital space are discussed. Additionally, an overview of the integration of associated tools such as artificial intelligence, machine learning and block-chain technology with graphene-based devices and structures is also presented.

show abstract

Section: The Meta-verse Of Composites Manufacturingmentioning

confidence: 99%

Graphene nanoparticles as data generating digital materials in industry 4.0

Ali

Irfan

Khan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Deep and machine learning, which have been rapidly evolving recently, are being used in various fields such as image and natural language processing to effectively identify the relationship between complex input and output. Additionally, machine learning has broadened its application to address issues with the current device module simulator 4 – 7 . Recent studies have shown that advances in machine learning models, such as deep neural networks, mostly focus on solutions for partial differential equations, such as Maxwell’s equations for calculating electromagnetic values 8 – 13 and there are few studies on grid-wise techniques.…”

Section: Introductionmentioning

confidence: 99%

Grid-wise simulation acceleration of the electromagnetic fields of 2D optical devices using super-resolution

Seo

Kim

Seok

2023

Sci Rep

View full text Add to dashboard Cite

The significance of simulation has been increasing in device design due to the cost of real test. The accuracy of the simulation increases as the resolution of the simulation increases. However, the high-resolution simulation is not suited for actual device design because the amount of computing exponentially increases as the resolution increases. In this study, we introduce a model that predicts high-resolution outcomes using low-resolution calculated values which successfully achieves high simulation accuracy with low computational cost. The fast residual learning super-resolution (FRSR) convolutional network model is a model that we introduced that can simulate electromagnetic fields of optical. Our model achieved high accuracy when using the super-resolution technique on a 2D slit array under specific circumstances and achieved an approximately 18 times faster execution time than the simulator. To reduce the model training time and enhance performance, the proposed model shows the best accuracy (R2: 0.9941) by restoring high-resolution images using residual learning and a post-upsampling method to reduce computation. It has the shortest training time among the models that use super-resolution (7000 s). This model addresses the issue of temporal limitations of high-resolution simulations of device module characteristics.

show abstract

“…This study proposes a novel solution to the problem using a deep-learning method called inverse covariance estimating generative adversarial network (ICEGAN). Numerous studies have sought to apply deep learning to various problems [15][16][17][18] because of recent advancements in deep learning models. Consequently, effective applications in image classification [19,20], object detection [21,22], a variety of natural language processing challenges, including language translation [23,24] and text generation [25,26], and financial portfolio management [27] have been developed.…”

Section: Introductionmentioning

confidence: 99%

ICEGAN: inverse covariance estimating generative adversarial network

Kim¹,

Lee²,

Seok³

2023

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Owing to the recent explosive expansion of deep learning, several challenging problems in a variety of fields have been handled by deep learning, yet deep learning methods have been limited in their application to the network estimation problem. While network estimation has a possibility to be a useful method in various domains, deep learning-based network estimation has a limitation in that the number of variables must be fixed and the estimation cannot be performed by convolutional layers. In this study, we propose a Generative Adversarial Network (GAN) based method, called Inverse Covariance Estimating GAN (ICEGAN), which can alleviate these limitations. In ICEGAN, the concepts in Cycle-Consistent Adversarial Networks (CycleGAN) are modified for the problem and employed to adopt gene expression data. Additionally, the Monte Carlo approach is used to address the fixed size in the network estimation process. Thus, sub-networks are sampled from the entire network and estimated by ICEGAN; then, the Monte Carlo approach reconstructs the entire network with the estimations. In the simulation study, ICEGAN demonstrated superior performances compared to conventional models and the ordinary GAN model in estimating networks. Specifically, ICEGAN outperformed an ordinary GAN by 85.9% on average when the models were evaluated using the area under curve. In addition, ICEGAN performed gene network estimation of breast cancer using a gene expression dataset. Consequently, ICEGAN demonstrated promising results, considering the deep learning-based network estimation and the proposed Monte Carlo approach for GAN models, both of which can be expanded to other domains.

show abstract

Simulator acceleration and inverse design of fin field-effect transistors using machine learning

Cited by 16 publications

References 12 publications

Graphene nanoparticles as data generating digital materials in industry 4.0

Graphene nanoparticles as data generating digital materials in industry 4.0

Grid-wise simulation acceleration of the electromagnetic fields of 2D optical devices using super-resolution

ICEGAN: inverse covariance estimating generative adversarial network

Contact Info

Product

Resources

About