Quantum Kernel Learning for Small Dataset Modeling in Semiconductor Fabrication: Application to Ohmic Contact

2024-09-17

AI Summary

Modeling Ohmic contacts in semiconductor manufacturing faces challenges including extremely limited data (only 159 experimental points), high dimensionality, and susceptibility to overfitting. Method: This work introduces quantum machine learning to this domain for the first time, proposing a novel data augmentation framework that synergistically combines a static two-layer ZZ feature map with a variational autoencoder (VAE), and constructs the first quantum kernel regressor (SQKR). SQKR integrates quantum state encoding, quantum kernel learning, and efficient kernel matrix computation. Contribution/Results: Evaluated on Ohmic contact resistance prediction, SQKR achieves a mean absolute error (MAE) of 0.314 Ω·mm—significantly outperforming six state-of-the-art classical models—and demonstrates strong robustness across multiple independent replications. This study establishes a generalizable quantum machine learning paradigm for high-dimensional industrial modeling under severe data scarcity.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Complex semiconductor fabrication processes, such as Ohmic contact formation in unconventional semiconductor devices, pose significant modeling challenges due to a large number of operational variables and the difficulty of collecting large, high-quality datasets. Classical machine learning (CML) models often struggle in such scenarios, where the data is both high-dimensional and limited in quantity, leading to overfitting and reduced predictive accuracy. To address this challenge, we develop the first application of quantum machine learning (QML) to model this semiconductor process, leveraging quantum systems' capacity to efficiently capture complex correlations in high-dimensional spaces and generalize well with small datasets. Using only 159 experimental samples augmented via a variational autoencoder, we report a quantum kernel-based regressor (SQKR) with a static 2-level ZZ feature map. The SQKR consistently outperformed six mainstream CML models across all evaluation metrics, achieving the lowest mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE), with repeated experiments confirming its robustness. Notably, SQKR achieved an MAE of 0.314 Ohm-mm with data from experimental verification, demonstrating its ability to effectively model semiconductor fabrication processes despite limited data availability. These results highlight QML's unique capability to handle small yet high-dimensional datasets in the semiconductor industry, making it a promising alternative to classical approaches for semiconductor process modeling.

Problem

• Modeling Ohmic contact formation with limited semiconductor data
• Overcoming classical ML struggles in high-dimensional small datasets
• Applying quantum kernel learning for superior predictive accuracy

Innovation

• Quantum kernel regressor for small datasets
• Static 2-level ZZ feature map
• Variational autoencoder data augmentation