Acceleration of Semiconductor Device Simulation with Approximate Solutions Predicted by Trained Neural Networks

Seung Cheol Han, Jonghyun Choi, Sung Min Hong

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)


In order to accelerate the semiconductor device simulation, we propose to use a neural network to learn an approximate solution for desired bias conditions. With an initial solution (predicted by a trained neural network) sufficiently close to the final one, the computational cost to calculate several unnecessary solutions is significantly reduced. Specifically, a convolutional neural network for the metal-oxide-semiconductor field-effect transistor (MOSFET) is trained in a supervised manner to compute the initial solution. In particular, we propose to consider a device template for various devices and a compact expression of the solution based on the electrostatic potential. We empirically show that the proposed method accelerates the simulation significantly.

Original languageEnglish
Pages (from-to)5483-5489
Number of pages7
JournalIEEE Transactions on Electron Devices
Issue number11
Publication statusPublished - 2021 Nov 1

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korea Government under Grant NRF-2019R1A2C1086656 and Grant NRF-2020M3H4A3081800 and in part by the Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea Government (MSIT), Development of Ultra Low-Power Mobile Deep Learning Semiconductor With Compression/Decompression of Activation/Kernel Data, under Grant 2019-0-01351.

Publisher Copyright:
© 1963-2012 IEEE.

All Science Journal Classification (ASJC) codes

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


Dive into the research topics of 'Acceleration of Semiconductor Device Simulation with Approximate Solutions Predicted by Trained Neural Networks'. Together they form a unique fingerprint.

Cite this