FV-Train: Quantum Convolutional Neural Network Training with a Finite Number of Qubits by Extracting Diverse Features

TL;DR

This paper introduces FV-Training, a novel quantum convolutional neural network training algorithm that optimizes feature extraction using a finite number of qubits, addressing the challenge of limited qubit resources in the NISQ era.

Contribution

It proposes a new training method for QCNNs that enhances feature extraction with limited qubits, improving performance in noisy quantum environments.

Findings

Effective feature extraction with finite qubits demonstrated

Reduces barren plateaus in quantum training

Improves QCNN performance in NISQ devices

Abstract

Quantum convolutional neural network (QCNN) has just become as an emerging research topic as we experience the noisy intermediate-scale quantum (NISQ) era and beyond. As convolutional filters in QCNN extract intrinsic feature using quantum-based ansatz, it should use only finite number of qubits to prevent barren plateaus, and it introduces the lack of the feature information. In this paper, we propose a novel QCNN training algorithm to optimize feature extraction while using only a finite number of qubits, which is called fidelity-variation training (FV-Training).