Deterministic Tensor Network Classifiers
Abstract
We present tensor networks for feature extraction and refinement of classifier performance. These networks can be initialised deterministically and have the potential for implementation on near-term intermediate-scale quantum (NISQ) devices. Feature extraction proceeds through a direct combination and compression of images amplitude-encoded over just qubits. Performance is refined using `Quantum Stacking', a deterministic method that can be applied to the predictions of any classifier regardless of structure, and implemented on NISQ devices using data re-uploading. These procedures are applied to a tensor network encoding of data, and benchmarked against the 10 class MNIST and fashion MNIST datasets. Good training and test accuracy are achieved without any variational training.
Cite
@article{arxiv.2205.09768,
title = {Deterministic Tensor Network Classifiers},
author = {L. Wright and F. Barratt and J. Dborin and V. Wimalaweera and B. Coyle and A. G. Green},
journal= {arXiv preprint arXiv:2205.09768},
year = {2022}
}