Parallel Proportional Fusion of Spiking Quantum Neural Network for Optimizing Image Classification
This work addresses the trainability and expressivity issues in hybrid quantum-classical neural networks for image classification, offering an incremental improvement in architecture design.
The paper tackled the limitations of serial hybrid quantum-classical neural networks by proposing a parallel proportional fusion architecture (PPF-QSNN) that combines spiking neural networks and variational quantum circuits, achieving improved performance on MNIST image classification with higher accuracy, lower loss, and better robustness compared to existing methods.
The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention due to the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations. However, the current investigated serial structure of HQCNN, wherein information sequentially passes from one network to another, often imposes limitations on the trainability and expressivity of the network. In this study, we introduce a novel architecture termed Parallel Proportional Fusion of Quantum and Spiking Neural Networks (PPF-QSNN). The dataset information is simultaneously fed into both the spiking neural network and the variational quantum circuits, with the outputs amalgamated in proportion to their individual contributions. We systematically assess the impact of diverse PPF-QSNN parameters on network performance for image classification, aiming to identify the optimal configuration. Numerical results on the MNIST dataset unequivocally illustrate that our proposed PPF-QSNN outperforms both the existing spiking neural network and the serial quantum neural network across metrics such as accuracy, loss, and robustness. This study introduces a novel and effective amalgamation approach for HQCNN, thereby laying the groundwork for the advancement and application of quantum advantage in artificial intelligent computations.