EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network

Wonjun Shin, Jiyong Im, Ryun-Han Koo, Jaehyeon Kim, Ki-Ryun Kwon, Dongseok Kwon, Jae-Joon Kim, Jong-Ho Lee, Daewoong Kwon iD

Advanced Science · 2023-05 · 10 (15)

DOI: 10.1002/advs.202207661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 27.03.2023. Verfasst von Wonjun Shin und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Inter-University Semiconductor Research Center, Seoul National University, Seoul, 08826, Republic …. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Samsung Research Funding & Incubation Center of Samsung Electronics, National Research Foundation (NRF) funded by the Korean Ministry of Science and ICT, BK21 FOUR program of the Education and Research Program for Future ICT Pioneers.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the recently increasing prevalence of deep learning, both academia and industry exhibit substantial interest in neuromorphic computing, which mimics the functional and structural features of the human brain. To realize neuromorphic computing, an energy‐efficient and reliable artificial synapse must be developed. In this study, the synaptic ferroelectric field‐effect‐transistor (FeFET) array is fabricated as a component of a neuromorphic convolutional neural network. Beyond the single transistor level, the long‐term potentiation and depression of synaptic weights are achieved at the array level, and a successful program‐inhibiting operation is demonstrated in the synaptic array, achieving a learning accuracy of 79.84% on the Canadian Institute for Advanced Research (CIFAR)‐10 dataset. Furthermore, an efficient self‐curing method is proposed to improve the endurance of the FeFET array by tenfold, utilizing the punch‐through current inherent to the device. Low‐frequency noise spectroscopy is employed to quantitatively evaluate the curing efficiency of the proposed self‐curing method. The results of this study provide a method to fabricate and operate reliable synaptic FeFET arrays, thereby paving the way for further development of ferroelectric‐based neuromorphic computing.

Schlagwörter

Stichwörter der Autor:innen

in-memory-computinglow-frequency noise (LFN)selective detectiontungsten oxide

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Inter-University Semiconductor Research Center, Seoul National University, Seoul, 08826, Republic of Korea.
  • Department of Electronic Engineering, Hanyang University, Seoul, 04763, South Korea.
  • Present address: Ministry of Science and ICT, Sejong, 30121, Republic of Korea.

ORCID-Profile: Daewoong Kwon

Förderung

  • Samsung Research Funding & Incubation Center of Samsung Electronics
  • National Research Foundation (NRF) funded by the Korean Ministry of Science and ICT
  • BK21 FOUR program of the Education and Research Program for Future ICT Pioneers

Zitieren

APA

Shin, W., Im, J., Koo, R. H., Kim, J., Kwon, K. R., Kwon, D., Kim, J. J., Lee, J. H., & Kwon, D. (2023). Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network. Advanced Science, 10(15). https://doi.org/10.1002/advs.202207661

Vancouver

Shin W, Im J, Koo RH, Kim J, Kwon KR, Kwon D, et al. Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network. Advanced Science. 2023;10(15). doi:10.1002/advs.202207661

BibTeX
@article{Shin2023,
  author = {Shin, Wonjun and Im, Jiyong and Koo, Ryun-Han and Kim, Jaehyeon and Kwon, Ki-Ryun and Kwon, Dongseok and Kim, Jae-Joon and Lee, Jong-Ho and Kwon, Daewoong},
  title = {Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network},
  journal = {Advanced Science},
  year = {2023},
  volume = {10},
  number = {15},
  doi = {10.1002/advs.202207661}
}
Kostenlos starten →