English

QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks

Quantum Physics 2022-09-28 v3 Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@article{arxiv.2110.03861,
  title  = {QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks},
  author = {Jun Qi and Chao-Han Huck Yang and Pin-Yu Chen},
  journal= {arXiv preprint arXiv:2110.03861},
  year   = {2022}
}

Comments

Preprint. A Non-archival and preliminary venue was presented in NeurIPS 2021, Quantum Tensor Networks in Machine Learning Workshop