.png){kind=icon}
返回
Variational quantum circuits for convolution and window-based image processing applications
.png){kind=icon}
PRE
AI
DOI：10.1088/2058-9565/ace378.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Quantum information processing is gaining popularity in the fields of machine learning and image processing because of its advantages. Quantum convolution is an interesting topic in this field, and studies on this topic can be divided into value-based and angle-based methods. Although quantum convolution studies on angle-based or variational quantum circuits (VQCs) is called convolution, the circuits work differently from classical convolution. In this study, contrary to the literature, the VQC was trained to imitate classical convolution. The differential evolution algorithm (DEA) was used to optimize the VQCs. The proposed method requires as many qubits as the filter size (N x N). The generated circuits contain N x N x 4 quantum gates and N x N x 3 trainable parameters. The generated circuits were tested in Python environment using Cirq simulator. The Cifar10 and MNIST datasets are used as examples. For 2 x 2 filters with different weights, the convolution was successfully modeled with a mean squared error of less than 0.001. In general, the proposed method imitates classic convolution within +/- 5% tolerance. In conclusion, VQCs that imitate classical convolution with fewer qubits and quantum gates than value-based methods were obtained.
Keyword:
quantum computing
quantum information processing
VQC
DEA
quantum convolution
期刊
IF:
5
论文数:
1.4K
被引数:
5.1K
机构
引用论文
Demonstration of Quantum Image Edge Extration Enhancement Through Improved Sobel Operator.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏TensorFlow Quantum: Impacts of Quantum State Preparation on Quantum Machine Learning PerformanceTensorFlow量子: 量子态制备对量子机器学习性能的影响IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏An improved differential evolution algorithm and its application in optimization problemSOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
分享收藏
查看更多内容