Random Quantum Neural Networks (RQNN) for Noisy Image Recognition

Abstract

Classical Random Neural Networks (RNNs) have demonstrated effective applications in decision making, signal processing, and image recognition tasks. However, their implementation has been limited to deterministic digital systems that output probability distributions in lieu of stochastic behaviors of random spiking signals. We introduce the novel class of supervised Random Quantum Neural Networks (RQNNs) with a robust training strategy to better exploit the random nature of the spiking RNN. The proposed RQNN employs hybrid classical-quantum algorithms with superposition state and amplitude encoding features, inspired by quantum information theory and the brain's spatial-temporal stochastic spiking property of neuron information encoding. We have extensively validated our proposed RQNN model, relying on hybrid classical-quantum algorithms via the PennyLane Quantum simulator with a limited number of qubits. Experiments on the MNIST, FashionMNIST, and KMNIST datasets demonstrate that the proposed RQNN model achieves an average classification accuracy of 94.9%. Additionally, the experimental findings illustrate the proposed RQNN's effectiveness and resilience in noisy settings, with enhanced image classification accuracy when compared to the classical counterparts (RNNs), classical Spiking Neural Networks (SNNs), and the classical convolutional neural network (AlexNet). Furthermore, the RQNN can deal with noise, which is useful for various applications, including computer vision in NISQ devices. The PyTorch code 1 is made available on GitHub to reproduce the results reported in this manuscript.

Programming Quantum Neural Networks on NISQ Systems: An Overview of Technologies and Methodologies

“…Few examples include image classification (MNIST dataset) [ 44 , 84 ], computational biology [ 85 ], and high-energy physics [ 86 ]. The QNN framework has found applications in image classification [ 87 ], cyber-security [ 88 ], medical [ 89 ], and high-energy physics problems [ 90 , 91 ]. has been used for image classification [ 66 ], remote sensing [ 92 ], and medical applications [ 93 ].…”

Hybrid Quantum Neural Network Image Anti-Noise Classification Model Combined with Error Mitigation

“…We compare the model proposed in this paper with other recent quantum neural network classification algorithms in noisy environments. Here, we classify the test subset of the FashionMNIST dataset using SQNN [47] and RQNN [48]. This experiment still selected 400 test samples.…”

Neural Network System for Recognizing Images Affected by Random-Valued Impulse Noise

“…Jang et al showed in their work that DNNs are susceptible to spatially uncorrelated white noise, and by introducing a noise learning procedure, it is possible to provide a better qualitative match to human performance [37]. In [38], a controlled random quantum neural network was proposed that used hybrid classical quantum algorithms with superposition and amplitude state coding functions, which improved not only the classification accuracy on MNIST, FashionMNIST, and KMNIST data, but also stability under conditions of increased noise. Also, a complex valued multilayer neural network with multivalued neurons (MLMVN) was adapted and successfully applied to filter impulse noise [39].…”