Design method and system of quantum convolutional neural network based on quantum circuit

• Main Authors: CHENG CHONGJIAN, YUAN SUZHEN, HE JUNTAO, XIA SHUYIN, LIN WENPING, QIAO ZHIQIN, LUO YUAN, LI JUNXI, DENG WENXI, WANG YAN, HU QINGXIANG, ZHANG JING
• Format: Patent
• Language: Chinese; English
• Published: 27.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention relates to a design method and system of a quantum convolutional neural network based on a quantum circuit, and belongs to the field of quantum computing. The method comprises the following steps: S1, standardizing an image to be classified, and partitioning the image according to a classic convolution method; s2, designing a quantum line of quantum image coding and convolution, and coding and processing the image partitioned in S1; s3, performing pooling processing on the image data processed in the S2, and extracting feature information on a plurality of quantum bits to one quantum bit; and S4, designing a quantum full-connection neural network to process and analyze the feature information pooled in the S3 and split the image. According to the method, quantum coding and preparation are optimized through a quantum data reloading method, so that consumption of the number of quantum bits of an algorithm model is reduced, the characteristics of partial connection and weight sharing of a classical