Saved in:
Bibliographic Details
Main Authors: Yan, Weiman, Chang, Yi-Chia, Zhao, Wanyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914414070857728
author Yan, Weiman
Chang, Yi-Chia
Zhao, Wanyu
author_facet Yan, Weiman
Chang, Yi-Chia
Zhao, Wanyu
contents Accurate and efficient circuit behavior modeling is a cornerstone of modern electronic design automation. Among different types of circuits, stiff circuits are challenging to model using previous frameworks. In this work, we propose a new approach using Crossformer, which is a current state-of-the-art Transformer model for time-series prediction tasks, combined with Kolmogorov-Arnold Networks (KANs), to model stiff circuit transient behavior. By leveraging the Crossformer's temporal representation capabilities and the enhanced feature extraction of KANs, our method achieves improved fidelity in predicting circuit responses to a wide range of input conditions. Experimental evaluations on datasets generated through SPICE simulations of analog-to-digital converter (ADC) circuits demonstrate the effectiveness of our approach, with significant reductions in training time and error rates.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stiff Circuit System Modeling via Transformer
Yan, Weiman
Chang, Yi-Chia
Zhao, Wanyu
Computational Engineering, Finance, and Science
Machine Learning
Accurate and efficient circuit behavior modeling is a cornerstone of modern electronic design automation. Among different types of circuits, stiff circuits are challenging to model using previous frameworks. In this work, we propose a new approach using Crossformer, which is a current state-of-the-art Transformer model for time-series prediction tasks, combined with Kolmogorov-Arnold Networks (KANs), to model stiff circuit transient behavior. By leveraging the Crossformer's temporal representation capabilities and the enhanced feature extraction of KANs, our method achieves improved fidelity in predicting circuit responses to a wide range of input conditions. Experimental evaluations on datasets generated through SPICE simulations of analog-to-digital converter (ADC) circuits demonstrate the effectiveness of our approach, with significant reductions in training time and error rates.
title Stiff Circuit System Modeling via Transformer
topic Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2510.24727