Abstract Summary/Description
Abstract: Music classification is a fundamental task in the fields of music information retrieval and sound processing, with applications ranging from music recommendation systems to genre classification. Traditional deep learning approaches, particularly Convolutional Neural Networks (CNNs), have shown great success in classifying music data. However, these methods often require large datasets and computational resources due to their deep architectures. Quantum computing, a novel computational paradigm, offers potential speedup for certain types of machine learning problems. In this project, we propose to explore the use of Quantum Convolutional Neural Networks (QCNNs) to improve the efficiency and performance of music classification tasks. The QCNN will leverage quantum circuits to replicate the functionality of classical CNNs while taking advantage of quantum parallelism and probabilistic sampling. We will develop a quantum-enhanced CNN model that includes both quantum convolutional layers and classical post-processing. By applying quantum gates and measurements, we will demonstrate how the QCNN can extract meaningful features from music spectrograms, allowing for faster and more efficient music classification. The focus of this project will be on the classification of musical genres and mood, with a potential reduction in the computational complexity traditionally associated with deep CNNs.