This year, the International Joint Conference on Neural Networks (IJCNN) took place in Rome, Italy, from June 30th to July 5th. There, Eduardo Mosqueira-Rey (PI in NEXT-GEN-SOMNUS), had the oportunity to present new work about exploring the performance of Quantum Support Vector Classifiers (QSVCs) and Quantum Neural Networks (QNNs) in comparison to classical models for machine learning tasks.
By evaluating these models on the multiple datasets, its shown that quantum models tend to outperform classical approaches as the problem complexity increases. While QSVCs generally provide more consistent results, QNNs exhibit superior performance in higher-complexity tasks due to their increased quantum load.
Additionally, an analysis on the impact of hyperparameter tuning was carried out, showing that feature maps and ansatz configurations significantly influence model accuracy. We also compare the PennyLane and Qiskit frameworks, concluding that Qiskit provides better optimization and efficiency for our implementation. These findings highlight the potential of Quantum Machine Learning (QML) for complex classification problems and provide insights into model selection and optimization strategies.