PulseAugur
EN
LIVE 12:30:33

Autoencoder framework enables rapid FinFET transistor modeling

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a machine learning framework using an autoencoder to efficiently model FinFET transistors. This autoencoder compresses current-voltage (I-V) curves into a latent space, capturing essential device physics and enabling accurate reconstruction of I-V data. The model can also directly extract key device metrics like threshold voltage and transconductance, demonstrating high accuracy with minimal training data for rapid device characterization and simulation. AI

IMPACT This research could accelerate the design and simulation of semiconductor devices by providing a more efficient modeling approach.

RANK_REASON The cluster contains an arXiv paper detailing a new research methodology for device modeling.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Autoencoder framework enables rapid FinFET transistor modeling

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Amit Sarkar Suman Sau, Swagata Mandal ·

    Rapid FinFET Modelling Using an Autoencoder

    arXiv:2606.24046v1 Announce Type: cross Abstract: This work presents a machine learning framework that leverages an autoencoder (AE) for the efficient modeling of FinFET. We first calibrated a BSIM-CMG model to generate a dataset of current-voltage (ID-VG) characteristics. This d…

  2. arXiv cs.LG TIER_1 English(EN) · Swagata Mandal ·

    Rapid FinFET Modelling Using an Autoencoder

    This work presents a machine learning framework that leverages an autoencoder (AE) for the efficient modeling of FinFET. We first calibrated a BSIM-CMG model to generate a dataset of current-voltage (ID-VG) characteristics. This data was used to train an autoencoder that compress…

RELATED ENTITIES

RELATED TOPICS