Multi-channel convolutional neural quantum embedding
This addresses the challenge of improving quantum machine learning efficacy for multi-channel data, though it appears incremental as it builds on existing quantum embedding methods.
The paper tackled the problem of optimizing quantum embedding for quantum supervised learning on classical data by introducing a classical-quantum hybrid approach that goes beyond standard quantum circuit limitations, achieving benchmarked performance on CIFAR-10 and Tiny ImageNet datasets.
Classification using variational quantum circuits is a promising frontier in quantum machine learning. Quantum supervised learning (QSL) applied to classical data using variational quantum circuits involves embedding the data into a quantum Hilbert space and optimizing the circuit parameters to train the measurement process. In this context, the efficacy of QSL is inherently influenced by the selection of quantum embedding. In this study, we introduce a classical-quantum hybrid approach for optimizing quantum embedding beyond the limitations of the standard circuit model of quantum computation (i.e., completely positive and trace-preserving maps) for general multi-channel data. We benchmark the performance of various models in our framework using the CIFAR-10 and Tiny ImageNet datasets and provide theoretical analyses that guide model design and optimization.