This project serves as the final examination for the Quantum Machine Learning module. The goal is to apply concepts learned throughout the course to solve real-world problems using quantum computing techniques.
In this report, we explored the application of convolutional neu ral networks (CNNs) and hybrid neural networks (HNNs) for binary classification tasks using the CIFAR-10 dataset. We con ducted three experiments, each focusing on distinguishing be tween different pairs of classes: airplane vs. automobile, cat vs. dog, and ship vs. truck. For each experiment, we trained both CNN and HNN models, analyzing their performance in terms of overall accuracy and class-wise accuracy. Results indicate that while both models demonstrate competitive performance, HNNs exhibit advantages in certain aspects, suggesting their potential superiority in specific scenarios.
models/: Contains the Python scripts and Jupyter Notebooks implementing the CNN model and the HNN model.Quantum_ML_Lab.pdf: This file is the report of the project.README.md: This file providing an overview of the project.