The Design of a Novel Hybrid Quantum Deep Neural Network in INEQR Images Classification

Abstract

Abstract We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby proposing a novel hybrid quantum deep neural network (HQDNN) which is used for image classification. After bilinear interpolation reduces the original image to a suitable size, INEQR is used to encode it into quantum states as the input of HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of PQCs are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of HQDNN, we conduct binary classification and three classification experiments on the MNIST data set. In the first binary classification, the accuracy of 0 and 4 exceeds $98\%$. Then we compared the performance of three classification with other algorithms, results on two datasets show that its classification accuracy is higher than that of QDNN and general quantum convolutional neural network.