APEX: Automating Parameter Extraction of Compact Models with Differential Neural Network Approximation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The traditional compact model parameter extraction highly depends on engineers' expertise, leading to a time-consuming and iterative process. To address the above issue, this paper proposes an automatic parameter extraction method for compact models, APEX. The proposed APEX framework adopts an artificial neural network (ANN) method as an approximation of compact models using model parameters as inputs and IV/CV data as outputs. The model parameters are efficiently extracted using an automatic differential mechanism based on the ANN-approximated compact model. Experimental results demonstrate that our proposed framework achieves good fitting accuracy and scalability across device structures when evaluating GAA and FinFET devices. A fitting error of less than 4% is achieved on the open-source benchmark.

Original languageEnglish
Title of host publication2025 International Symposium of Electronics Design Automation, ISEDA 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages622-627
Number of pages6
ISBN (Electronic)9798331536961
DOIs
StatePublished - 2025
Event2025 International Symposium of Electronics Design Automation, ISEDA 2025 - Hong Kong, China
Duration: 9 May 202512 May 2025

Publication series

Name2025 International Symposium of Electronics Design Automation, ISEDA 2025

Conference

Conference2025 International Symposium of Electronics Design Automation, ISEDA 2025
Country/TerritoryChina
CityHong Kong
Period9/05/2512/05/25

Keywords

  • Compact model
  • automatic differentiation
  • neural network
  • parameter extraction

Fingerprint

Dive into the research topics of 'APEX: Automating Parameter Extraction of Compact Models with Differential Neural Network Approximation'. Together they form a unique fingerprint.

Cite this