A Hierarchical Fused Quantum Fuzzy Neural Network for Image Classification

TL;DR

Different from classical FDNN, HQFNN uses quantum neural networks to learn fuzzy membership functions in fuzzy neural network, and the results show that the proposed model can outperform several existing methods.

Abstract

Neural network is a powerful learning paradigm for data feature learning in the era of big data. However, most neural network models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to address this problem. FDNN is a hierarchical deep neural network that derives information from both fuzzy and neural representations, the representations are then fused to form representation to be classified. FDNN perform well on uncertain data classification tasks. In this paper, we proposed a novel hierarchical fused quantum fuzzy neural network (HQFNN). Different from classical FDNN, HQFNN uses quantum neural networks to learn fuzzy membership functions in fuzzy neural network. We conducted simulated experiment on two types of datasets (Dirty-MNIST and 15-Scene), the results show that the proposed model can outperform several existing methods. In addition, we demonstrate the robustness of the proposed quantum circuit.

Figures (10)

• Figure 1: The structure of HQFNN. It is composed of four parts that respectively address different learning tasks, i.e. quantum fuzzy logic representation, deep neural network representation, fusion layer and classifier layer.
• Figure 2: Quantum circuit with single-qubit for quantum member function.
• Figure 3: Samples from Dirty-MNIST dataset.
• Figure 4: Samples from 15-Scene dataset.
• Figure 5: The convergence analysis of the training on Dirty-MNIST.