发表机构
Centre for High Energy Physics, Indian Institute of Science（印度科学研究所高能物理中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出一种经典 - 量子混合的图像分类策略，量子部分含图像幅度编码等操作，多个专家用不同参数处理图像并提取特征，经典部分联合处理特征进行预测。实验表明该策略优于单个专家分析，降低预测失败率，在GPU上开销适中，还可在量子处理器执行。
AI 中文摘要
模式识别问题出现在各种物理图像处理情况中，卷积神经网络是用于所需特征提取和分类任务的流行方案。经典网络使用基于扩散的模糊和逐块池化来对图像数据进行下采样并捕获重要结构特征。在这项工作中，我们提出并展示了一种更有效的包含专家混合的量子启发策略。它是一个经典 - 量子混合框架。量子部分包括图像的幅度编码、使用局部酉操作的卷积、多个专家用不同参数处理同一图像以及使用量子稳定器码进行特征提取。经典部分然后使用标准全连接神经网络联合处理不同专家提取的特征以进行图像类别预测。使用MNIST和Fashion - MNIST数据集作为基准，我们证明联合专家分析优于单个专家分析，并将图像类别预测的失败率降低了约两倍。我们的量子启发策略在GPU工作站上的开销仅为中等，这使我们的方案成为现有经典方案的实用替代方案。我们还指出了我们框架的量子部分如何在量子处理器上执行。
英文摘要
Pattern recognition problems arise in a variety of physical image processing situations, and convolutional neural networks are a popular scheme for the required feature extraction and classification tasks. The classical networks use diffusion-based smearing and block-wise pooling to downsample the image data and capture important structural features. In this work, we propose and demonstrate a more efficient quantum-inspired strategy involving a mixture of experts. It is a hybrid classical-quantum framework. The quantum part consists of amplitude encoding of the images, convolution using local unitary operations, multiple experts processing the same image with different parameters, and feature extraction using quantum stabiliser codes. The classical part then jointly processes the features extracted by different experts using a standard fully connected neural network for image class prediction. Using MNIST and Fashion-MNIST datasets as benchmarks, we demonstrate that the joint expert analysis outperforms the individual expert one, as well as reduces the failure rate of image class prediction by around a factor of two. The overhead of our quantum-inspired strategy is only moderate on GPU workstations, which makes our proposal a practical alternative to existing classical schemes. We also point out how the quantum part of our framework can be executed on a quantum processor.
Comments14 pages, 18 figures, comments welcome (v2) The number of features extracted from the images is considerably reduced, which simplifies the subsequent classification. The results are essentially the same
