An end-to-end trainable hybrid classical-quantum classifier

TL;DR

This paper presents a hybrid classical-quantum classifier combining tensor networks and variational quantum circuits, trained end-to-end, improving feature extraction for image classification tasks like MNIST.

Contribution

It introduces a novel end-to-end trainable hybrid model that integrates tensor networks with quantum circuits for supervised learning.

Findings

Tensor network-based feature extraction outperforms PCA.

The architecture is adaptable to different quantum resource availabilities.

The model achieves better classification accuracy on MNIST datasets.

Abstract

We introduce a hybrid model combining a quantum-inspired tensor network and a variational quantum circuit to perform supervised learning tasks. This architecture allows for the classical and quantum parts of the model to be trained simultaneously, providing an end-to-end training framework. We show that compared to the principal component analysis, a tensor network based on the matrix product state with low bond dimensions performs better as a feature extractor for the input data of the variational quantum circuit in the binary and ternary classification of MNIST and Fashion-MNIST datasets. The architecture is highly adaptable and the classical-quantum boundary can be adjusted according the availability of the quantum resource by exploiting the correspondence between tensor networks and quantum circuits.