This document is a research paper published on Quantum Machine Learning as a final project under the course of Quantum Computing. Abstract:This paper explores the integration of quantum computing and machine learning, focusing on the development and performance of Quantum Convolutional Neural Networks (QCNNs) compared to classical Convolutional Neural Networks (CNNs). Foundational quantum concepts such as quantum gates, circuits, and algorithms are examined, alongside their applications in machine learning tasks. A case study is conducted where QCNNs and CNNs are applied to the MNIST dataset for multi-class classification. Results indicate that QCNNs outperform CNNs as the number of classes increases, achieving higher accuracy with fewer parameters and demonstrating better generalization, particularly for datasets with limited samples. The study highlights QCNN’s potential in leveraging quantum properties like superposition and entanglement for more efficient learning. Finally, the paper discusses challenges in quantum machine learning, such as noise, limited qubits, and high computational costs, while outlining expected advancements that may further enhance quantum learning’s applicability.