International Conference on Optical Communications and Networks (ICOCN)
Simulation Study on Dataset Classification Based on Quantum Neural Networks
Jing Wang, Huan Chen, Junsen Lai
Abstract
Application exploration based on quantum algorithms has emerged as a research hotspot in recent years. As an interdisciplinary integration product of quantum computing theory and artificial neural networks, Quantum Neural Networks (QNNs) are expected to provide effective solutions to problems such as dataset classification. Taking the Wine dataset as the research object, this paper conducts a classification simulation study based on QNNs. By adopting the control variable method, we compare the impacts of different optimizers, data augmentation methods, quantum measurement methods, input encoding methods, feature combination types and noise intensities on classification performance, with accuracy, precision and F1-score set as the core evaluation metrics.