Machine learning is actively being explored for its potential to design, validate, and even hybridize with near-term quantum devices. A central question is whether neural networks can provide a tractable representation of a given quantum state of interest. When true, stochastic neural networks can be employed for many unsupervised tasks, including generative modeling and state tomography. However, to be applicable for real experiments, such methods must be able to encode quantum mixed states. Here, we parametrize a density matrix based on a restricted Boltzmann machine that is capable of purifying a mixed state through auxiliary degrees of freedom embedded in the latent space of its hidden units. We implement the algorithm numerically and use it to perform tomography on some typical states of entangled photons, achieving fidelities competitive with standard techniques.

中文翻译：

---

通过神经密度算子的潜在空间净化

人们正在积极探索机器学习在设计，验证，甚至与近期量子设备混合方面的潜力。中心问题是神经网络是否可以提供感兴趣的给定量子状态的可表示形式。如果为真，则随机神经网络可用于许多无人监督的任务，包括生成建模和状态层析成像。然而，为了适用于实际实验，这些方法必须能够编码量子混合态。在这里，我们对基于受限玻尔兹曼机器的密度矩阵进行参数化，该机器能够通过嵌入在其隐藏单元的潜在空间中的辅助自由度来净化混合状态。我们以数字方式实施该算法，并使用它对纠缠光子的某些典型状态进行层析成像，