PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics

Y. D. Ko, J. H. Lee, K. E. Kweon, T. H. Moon, J. M. Myoung, I. Yun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, the neural network based modeling for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy was investigated. In order to build the process model, the error back-propagation neural network was carried out and the X-ray diffraction data were used to analyze the characteristic variation for the different process conditions and predict the response models for the electrical characteristics. Principal component analysis was selected to reduce the dimension of the data sets. The compressed data were then used in the neural network. Those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

Original languageEnglish
Title of host publication2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages181-184
Number of pages4
ISBN (Print)0780393392, 9780780393394
DOIs
Publication statusPublished - 2005 Jan 1
Event2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC - Howloon, Hong Kong
Duration: 2005 Dec 192005 Dec 21

Publication series

Name2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC

Other

Other2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC
CountryHong Kong
CityHowloon
Period05/12/1905/12/21

Fingerprint

Molecular beam epitaxy
Neural networks
Thin films
Backpropagation
Principal component analysis
Hysteresis
Capacitance
Metals
Sampling
X ray diffraction

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Ko, Y. D., Lee, J. H., Kweon, K. E., Moon, T. H., Myoung, J. M., & Yun, I. (2005). PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics. In 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC (pp. 181-184). [1635235] (2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EDSSC.2005.1635235
Ko, Y. D. ; Lee, J. H. ; Kweon, K. E. ; Moon, T. H. ; Myoung, J. M. ; Yun, I. / PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics. 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC. Institute of Electrical and Electronics Engineers Inc., 2005. pp. 181-184 (2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC).
@inproceedings{b3ce262861384d3fb5d6b4b3db92f8e4,
title = "PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics",
abstract = "In this paper, the neural network based modeling for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy was investigated. In order to build the process model, the error back-propagation neural network was carried out and the X-ray diffraction data were used to analyze the characteristic variation for the different process conditions and predict the response models for the electrical characteristics. Principal component analysis was selected to reduce the dimension of the data sets. The compressed data were then used in the neural network. Those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.",
author = "Ko, {Y. D.} and Lee, {J. H.} and Kweon, {K. E.} and Moon, {T. H.} and Myoung, {J. M.} and I. Yun",
year = "2005",
month = "1",
day = "1",
doi = "10.1109/EDSSC.2005.1635235",
language = "English",
isbn = "0780393392",
series = "2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "181--184",
booktitle = "2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC",
address = "United States",

}

Ko, YD, Lee, JH, Kweon, KE, Moon, TH, Myoung, JM & Yun, I 2005, PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics. in 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC., 1635235, 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC, Institute of Electrical and Electronics Engineers Inc., pp. 181-184, 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC, Howloon, Hong Kong, 05/12/19. https://doi.org/10.1109/EDSSC.2005.1635235

PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics. / Ko, Y. D.; Lee, J. H.; Kweon, K. E.; Moon, T. H.; Myoung, J. M.; Yun, I.

2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC. Institute of Electrical and Electronics Engineers Inc., 2005. p. 181-184 1635235 (2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics

AU - Ko, Y. D.

AU - Lee, J. H.

AU - Kweon, K. E.

AU - Moon, T. H.

AU - Myoung, J. M.

AU - Yun, I.

PY - 2005/1/1

Y1 - 2005/1/1

N2 - In this paper, the neural network based modeling for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy was investigated. In order to build the process model, the error back-propagation neural network was carried out and the X-ray diffraction data were used to analyze the characteristic variation for the different process conditions and predict the response models for the electrical characteristics. Principal component analysis was selected to reduce the dimension of the data sets. The compressed data were then used in the neural network. Those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

AB - In this paper, the neural network based modeling for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy was investigated. In order to build the process model, the error back-propagation neural network was carried out and the X-ray diffraction data were used to analyze the characteristic variation for the different process conditions and predict the response models for the electrical characteristics. Principal component analysis was selected to reduce the dimension of the data sets. The compressed data were then used in the neural network. Those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

UR - http://www.scopus.com/inward/record.url?scp=43549092238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43549092238&partnerID=8YFLogxK

U2 - 10.1109/EDSSC.2005.1635235

DO - 10.1109/EDSSC.2005.1635235

M3 - Conference contribution

AN - SCOPUS:43549092238

SN - 0780393392

SN - 9780780393394

T3 - 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC

SP - 181

EP - 184

BT - 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ko YD, Lee JH, Kweon KE, Moon TH, Myoung JM, Yun I. PCA-based neural network modeling of MBE-grown HfO2 thin film characteristics. In 2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC. Institute of Electrical and Electronics Engineers Inc. 2005. p. 181-184. 1635235. (2005 IEEE Conference on Electron Devices and Solid-State Circuits, EDSSC). https://doi.org/10.1109/EDSSC.2005.1635235