Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement

TL;DR

This paper introduces a dual-qubit hierarchical fuzzy neural network leveraging quantum entanglement to model feature dependencies, improving classification accuracy and robustness in noisy conditions compared to classical and previous quantum models.

Contribution

It proposes a novel dual-qubit quantum neural network that encodes feature pairs with entanglement, enabling relational learning and outperforming prior models in accuracy and noise robustness.

Findings

Higher classification accuracy than QA-HFNN and classical baselines

Demonstrates relational modeling capability via entanglement

Robust against noisy data and suitable for NISQ devices

Abstract

Classical deep neural network models struggle to represent data uncertainty and capture dependencies between features simultaneously, especially under fuzzy or noisy conditions. Although a quantum-assisted hierarchical fuzzy neural network (QA-HFNN) was proposed to learn fuzzy membership for each feature, it cannot model dependencies between features due to its single-qubit encoding. To address this, this paper proposes a dual-qubit hierarchical fuzzy neural network (DQ-HFNN), encoding feature pairs onto a pair of entangled qubits, which extends the single-feature fuzzy model to a joint fuzzy representation. By introducing quantum entanglement, the dual-qubit circuit can encode non-classical correlations, enabling the model to directly learn relationship patterns between feature pairs. Experiments on benchmarks show that DQ-HFNN demonstrates higher classification accuracy than QA-HFNN, as well as classical deep learning baselines. Furthermore, ablation studies after controlling for circuit depth and parameter counts show that the performance gain mainly stems from the relational modeling capability enabled by entanglement rather than enhanced expressivity. The proposed DQ-HFNN model exhibits high parameter efficiency and fast inference speed. Experiments under noisy conditions suggest that it is robust against noise and has the potential to be implemented on noisy intermediate-scale quantum devices.