Hi 👋, my name is Tak. I am a Ph.D. student at Yonsei university (q-DNA) specializing in quantum machine learning. I am planning to share some of my works and thoughts through this blog. If you are interested have a look! And feel free to reach out if you have any questions, suggestions, or comments!
We propose a neural quantum embedding (NQE) technique based on deterministic quantum computation with one qubit (DQC1). Training NQE is efficiently achieved using DQC1, which is specifically designed for ensemble quantum systems, such as nuclear magnetic resonance (NMR).
Recent studies have revealed shortcomings in current generalization theories, particularly those relying on uniform bounds, across both classical and quantum settings. In this work, we present a margin-based generalization bound for QML models, providing a more reliable framework for evaluating generalization.
Quantum embedding is an essential step in quantum machine learning, and has substantial impacts on performance outcomes. Here, we present Neural Quantum Embedding (NQE), a method that efficiently optimizes quantum embedding by leveraging classical deep learning techniques.
We investigate the performance of various QCNN models differentiated by structures of parameterized quantum circuits, quantum data encoding methods, classical data pre-processing methods, cost functions and optimizers on MNIST and Fashion MNIST datasets.