HQFNN: A Compact Quantum-Fuzzy Neural Network for Accurate Image Classification

TL;DR

This paper introduces HQFNN, a compact quantum-fuzzy neural network that integrates fuzzy inference within a shallow quantum circuit coupled with classical features, achieving high accuracy and robustness in image classification with fewer parameters.

Contribution

It presents the first quantum-fuzzy neural network that embeds the entire fuzzy pipeline in a shallow quantum circuit, enhancing interpretability and efficiency for image classification.

Findings

Outperforms classical and quantum baselines on image benchmarks.

Uses several orders of magnitude fewer trainable weights.

Maintains accuracy under simulated quantum noise.

Abstract

Deep learning vision systems excel at pattern recognition yet falter when inputs are noisy or the model must explain its own confidence. Fuzzy inference, with its graded memberships and rule transparency, offers a remedy, while parameterized quantum circuits can embed features in richly entangled Hilbert spaces with striking parameter efficiency. Bridging these ideas, this study introduces a innovative Highly Quantized Fuzzy Neural Network (HQFNN) that realises the entire fuzzy pipeline inside a shallow quantum circuit and couples the resulting quantum signal to a lightweight CNN feature extractor. Each image feature is first mapped to a single qubit membership state through repeated angle reuploading. Then a compact rule layer refines these amplitudes, and a clustered CNOT defuzzifier collapses them into one crisp value that is fused with classical features before classification. Evaluated on standard image benchmarks, HQFNN consistently surpasses classical, fuzzy enhanced and quantum only baselines while using several orders of magnitude fewer trainable weights, and its accuracy degrades only marginally under simulated depolarizing and amplitude damping noise, evidence of intrinsic robustness. Gate count analysis further shows that circuit depth grows sublinearly with input dimension, confirming the model's practicality for larger images. These results position the model as a compact, interpretable and noise tolerant alternative to conventional vision backbones and provide a template for future quantum native fuzzy learning frameworks.