Random Quantum Neural Networks (RQNN) for Noisy Image Recog- nition

TitleRandom Quantum Neural Networks (RQNN) for Noisy Image Recog- nition
Publication TypeJournal Article
Year of Publication2022
AuthorsKonar D, Gelenbe E, Bhandary S, Sarma ADas, Cangi A
Journal ARXIV

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 be-
haviors 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 super-
position 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 ex-
tensively 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 av-
erage 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.


Historia zmian

Data aktualizacji: 10/11/2022 - 18:58; autor zmian: Sami Erol Gelenbe (seg@iitis.pl)