Understanding how the D-Wave quantum computer could be used for machine learning problems is of growing interest. Our work evaluates the feasibility of using the D-Wave as a sampler for machine learning. We describe a hybrid system that combines a classical deep neural network autoencoder with a quantum annealing Restricted Boltzmann Machine (RBM) using the D-Wave. We evaluate our hybrid autoencoder algorithm using two datasets, the MNIST dataset and MNIST Fashion dataset. We evaluate the quality of this method by using a downstream classification method where the training is based on quantum RBM-generated samples. Our method overcomes two key limitations in the current 2000-qubit D-Wave processor, namely the limited number of qubits available to accommodate typical problem sizes for fully connected quantum objective functions and samples that are binary pixel representations. As a consequence of these limitations we are able to show how we achieved nearly a 22-fold compression factor of grayscale 28 x 28 sized images to binary 6 x 6 sized images with a lossy recovery of the original 28 x 28 grayscale images. We further show how generating samples from the D-Wave after training the RBM, resulted in 28 x 28 images that were variations of the original input data distribution, as opposed to recreating the training samples. We formulated an MNIST classification problem using a deep convolutional neural network that used samples from a quantum RBM to train the MNIST classifier and compared the results with an MNIST classifier trained with the original MNIST training data set, as well as an MNIST classifier trained using classical RBM samples. Our hybrid autoencoder approach indicates advantage for RBM results relative to the use of a current RBM classical computer implementation for image-based machine learning and even more promising results for the next generation D-Wave quantum system.

中文翻译：

---

启用混合量子的 RBM 优势：用于量子图像压缩和生成学习的卷积自动编码器

了解 D-Wave 量子计算机如何用于机器学习问题越来越引起人们的兴趣。我们的工作评估了使用 D-Wave 作为机器学习采样器的可行性。我们描述了一个混合系统，它使用 D-Wave 将经典的深度神经网络自动编码器与量子退火受限玻尔兹曼机 (RBM) 相结合。我们使用两个数据集 MNIST 数据集和 MNIST 时尚数据集来评估我们的混合自动编码器算法。我们通过使用下游分类方法评估该方法的质量，其中训练基于量子 RBM 生成的样本。我们的方法克服了当前 2000 量子比特 D-Wave 处理器的两个关键限制，即有限数量的量子位可用于适应全连接量子目标函数和二进制像素表示样本的典型问题大小。由于这些限制，我们能够展示我们如何通过原始 28 x 28 灰度图像的有损恢复将灰度 28 x 28 尺寸图像的近 22 倍压缩因子实现为二进制 6 x 6 尺寸图像。我们进一步展示了如何在训练 RBM 后从 D-Wave 生成​​样本，产生 28 x 28 图像，这些图像是原始输入数据分布的变化，而不是重新创建训练样本。我们使用深度卷积神经网络制定了一个 MNIST 分类问题，该网络使用来自量子 RBM 的样本来训练 MNIST 分类器，并将结果与​​使用原始 MNIST 训练数据集训练的 MNIST 分类器以及使用经典训练的 MNIST 分类器进行比较。 RBM 样本。我们的混合自动编码器方法表明，相对于将当前 RBM 经典计算机实现用于基于图像的机器学习，以及对于下一代 D-Wave 量子系统而言，RBM ​​结果具有更大的优势。