用随机量子电路实现量子卷积，提升模型收敛速度
Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencoder
- 设计随机量子电路模拟卷积操作，生成新数据表征
- 性能接近经典CNN，部分场景下收敛更快
- 适合对量子机器学习加速感兴趣的科研人员
量子机器学习结合量子理论与经典机器学习算法。现有研究关注利用量子力学或量子信息理论加速学习时间或提升收敛性，也有研究探索在量子信息空间中进行数据变换以评估鲁棒性和性能提升。本文聚焦于使用随机量子电路作为量子卷积，对输入数据进行处理，生成可用于卷积网络的新表示。实验结果表明，其性能可与经典卷积神经网络相媲美，在某些情况下还能加速收敛。
原文摘要 · Abstract (English)
Quantum machine learning deals with leveraging quantum theory with classic machine learning algorithms. Current research efforts study the advantages of using quantum mechanics or quantum information theory to accelerate learning time or convergence. Other efforts study data transformations in the quantum information space to evaluate robustness and performance boosts. This paper focuses on processing input data using randomized quantum circuits that act as quantum convolutions producing new representations that can be used in a convolutional network. Experimental results suggest that the performance is comparable to classic convolutional neural networks, and in some instances, using quantum convolutions can accelerate convergence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。