arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02862cs.CVcs.LG
收藏

用于图像分类的量子经典混合机器学习(ICCAD特别会议论文)

Quantum-Classical Hybrid Machine Learning for Image Classification (ICCAD Special Session Paper)

Penn State University(宾夕法尼亚州立大学);IBM Corporation(国际商业机器公司)

Mahabubul Alam, Satwik Kundu, Rasit Onur Topaloglu, Swaroop Ghosh

摘要:

图像分类是传统深度学习的主要应用领域。量子机器学习(QML)有可能彻底改变图像分类。在任何典型的基于DL的图像分类中,我们使用卷积神经网络(CNN)从图像中提取特征,并使用多层感知器网络(MLP)创建实际的决策边界。一方面,QML模型在这两个任务中都很有用。参数化量子电路卷积(Quanvolution)可以从图像中提取丰富的特征。另一方面,量子神经网络(QNN)模型可以创建复杂的决策边界。因此,Quanvolution和QNN可用于创建用于图像分类的端到端QML模型。或者,我们可以使用经典的降维技术(如主成分分析(PCA)或卷积自动编码器(CAE))分别提取图像特征,并使用提取的特征来训练QNN。我们回顾了两个建议的量子经典混合ML模型的图像分类,即量子卷积神经网络和降维使用的经典算法,其次是QNN。特别是,我们在Quanvolution和基于CAE的图像数据集特征提取(而不是使用线性变换(如PCA)的降维)中使用可训练滤波器。我们讨论了这些模型的各种设计选择、潜在机会和缺点。我们还发布了一个基于Python的框架来创建和探索这些具有各种设计选择的混合模型。

英文摘要:

Image classification is a major application domain for conventional deep learning (DL). Quantum machine learning (QML) has the potential to revolutionize image classification. In any typical DL-based image classification, we use convolutional neural network (CNN) to extract features from the image and multi-layer perceptron network (MLP) to create the actual decision boundaries. On one hand, QML models can be useful in both of these tasks. Convolution with parameterized quantum circuits (Quanvolution) can extract rich features from the images. On the other hand, quantum neural network (QNN) models can create complex decision boundaries. Therefore, Quanvolution and QNN can be used to create an end-to-end QML model for image classification. Alternatively, we can extract image features separately using classical dimension reduction techniques such as, Principal Components Analysis (PCA) or Convolutional Autoencoder (CAE) and use the extracted features to train a QNN. We review two proposals on quantum-classical hybrid ML models for image classification namely, Quanvolutional Neural Network and dimension reduction using a classical algorithm followed by QNN. Particularly, we make a case for trainable filters in Quanvolution and CAE-based feature extraction for image datasets (instead of dimension reduction using linear transformations such as, PCA). We discuss various design choices, potential opportunities, and drawbacks of these models. We also release a Python-based framework to create and explore these hybrid models with a variety of design choices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑