QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
This work addresses the problem of fully quantum learning tasks for researchers in quantum machine learning, but it appears incremental as it builds on existing quantum embedding and variational quantum circuit methods.
The paper tackles the challenge of designing quantum neural networks for noisy intermediate-scale quantum computers by proposing QTN-VQC, an end-to-end learning framework that uses a trainable quantum tensor network for quantum embedding on a variational quantum circuit, and demonstrates advantages over other quantum embedding approaches on the MNIST dataset.
The advent of noisy intermediate-scale quantum (NISQ) computers raises a crucial challenge to design quantum neural networks for fully quantum learning tasks. To bridge the gap, this work proposes an end-to-end learning framework named QTN-VQC, by introducing a trainable quantum tensor network (QTN) for quantum embedding on a variational quantum circuit (VQC). The architecture of QTN is composed of a parametric tensor-train network for feature extraction and a tensor product encoding for quantum embedding. We highlight the QTN for quantum embedding in terms of two perspectives: (1) we theoretically characterize QTN by analyzing its representation power of input features; (2) QTN enables an end-to-end parametric model pipeline, namely QTN-VQC, from the generation of quantum embedding to the output measurement. Our experiments on the MNIST dataset demonstrate the advantages of QTN for quantum embedding over other quantum embedding approaches.