人工神经网络
可扩展性
量子
计算机科学
人工智能
物理
量子力学
数据库
作者
Batuhan Hangun,Onder Eyecioglu,Mehar Ali,Oguz Altun,Korhan Kayışlı
标识
DOI:10.1007/s11128-026-05387-8
摘要
Abstract Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning that aims to enhance classical learning methods by leveraging principles such as superposition and entanglement. However, skepticism remains regarding its practical advantages, particularly due to the limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns through a systematic evaluation of Quantum Neural Networks (QNNs), quantum-inspired counterparts of Artificial Neural Networks (ANNs). We construct and analyze 12 distinct QNN configurations by combining two quantum feature maps with six entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset show that QNNs can achieve competitive or superior performance compared to classical baseline models, with the best-performing configuration (QNN-3) reaching an R 2 score of up to 0.94 when forecasting wind power output using four input features. In addition, we provide a detailed analysis of simulation time across different configurations, highlighting trade-offs between model complexity and computational cost. These findings demonstrate the potential of QNNs as viable models for predictive tasks and contribute to the ongoing evaluation of QML in real-world applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI