The current practice of manually tuning quantum dots (QDs) for qubit operation is a relatively time-consuming procedure inherently impractical for scaling up and applications. In this work, we report on the {} implementation of a recently proposed auto-tuning protocol that combines machine learning (ML) with an optimization routine to navigate the parameter space. In particular, we show that a ML algorithm trained using exclusively simulated data to quantitatively classify the state of double QD device can be used to replace human heuristics in tuning of gate voltages in real devices. We demonstrate active feedback of a functional double dot device operated at millikelvin temperatures and discuss success rates as a function of initial conditions and device performance. Modifications to the training network, fitness function, and optimizer are discussed as a path towards further improvement in the success rate when starting both near and far detuned from the target double dot range.

中文翻译：

---

利用机器学习原位双点设备自动调整

手动调整量子点（QD）以进行qubit操作的当前做法是一个相对耗时的过程，它对于按比例放大和应用是固有地不切实际的。在这项工作中，我们报告了{@}最近提出的自动调整协议的实现，该协议结合了机器学习（ML）和优化例程来导航参数空间。特别是，我们表明，使用专门模拟的数据训练的ML算法可以定量地对双QD设备的状态进行分类，可以用来代替人类启发式技术来调整实际设备中的栅极电压。我们展示了在毫ikelvin温度下运行的功能性双点设备的主动反馈，并讨论了作为初始条件和设备性能的函数的成功率。修改训练网络，适应性功能，