A Hierarchical Fused Quantum Fuzzy Neural Network for Image Classification
This work addresses uncertainty handling in image classification for AI applications, but it appears incremental as it builds on classical fuzzy neural networks by incorporating quantum elements.
The paper tackles the problem of uncertainty in data for image classification by proposing a hierarchical fused quantum fuzzy neural network (HQFNN), which outperforms existing methods on datasets like Dirty-MNIST and 15-Scene.
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.