Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent’s memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach–Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.

中文翻译：

---

通过单光子量子行走实现可解释的量子机器学习


变分量子算法代表了一种有前途的量子机器学习方法，其中经典神经网络被参数化量子电路取代。然而，这两种方法都存在明显的局限性，即缺乏可解释性。在这里，我们提出了一种量化投影模拟（PS）的变分方法，这是一种旨在可解释人工智能的强化学习模型。 PS 中的决策被建模为描述智能体记忆的图上的随机游走。为了实现量化模型，我们考虑了通过变分算法训练的可调谐马赫-曾德尔干涉仪晶格中单光子的量子行走。通过使用迁移学习的示例，我们表明量化 PS 模型可以利用量子干涉来获得超越其经典模型的能力。最后，我们讨论了量子干扰在训练和跟踪决策过程中的作用，为实现可解释的量子学习代理铺平了道路。