A Novel Neural-Network Device Modeling Based on Physics-Informed Machine Learning-Reference-Cited by-同舟云学术

A Novel Neural-Network Device Modeling Based on Physics-Informed Machine Learning

Published:2023-11 Issue:11 Volume:70 Page:6021-6025
ISSN:0018-9383
Container-title:IEEE Transactions on Electron Devices
language:
Short-container-title:IEEE Trans. Electron Devices

Author:

Kim Bokyeom¹^ORCID,Shin Mincheol¹^ORCID

Affiliation:

1. School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

Funder

Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Science and Information Communication Technology

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Electronic, Optical and Magnetic Materials

Link

http://xplorestaging.ieee.org/ielx7/16/10294316/10271263.pdf?arnumber=10271263

Reference17 articles.

1. Adaptive activation functions accelerate convergence in deep and physics-informed neural networks

2. Direct Solution of the Boltzmann Transport Equation and Poisson–SchrÖdinger Equation for Nanoscale MOSFETs

3. Adam: A method for stochastic optimization;kingma;arXiv 1412 6980,2014

4. Searching for activation functions;ramachandran;arXiv 1710 05941,2017

5. Simulation of Silicon Nanowire Transistors Using Boltzmann Transport Equation Under Relaxation Time Approximation

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Accurate and fast electrostatic simulation of double gate FETs using deep neural network;2024 8th IEEE Electron Devices Technology & Manufacturing Conference (EDTM);2024-03-03