QFlow lite dataset: A machine-learning approach to the charge states in quantum dot experiments

Abstract

BackgroundOver the past decade, machine learning techniques have revolutionized how research and science are done, from designing new materials and predicting their properties to data mining and analysis to assisting drug discovery to advancing cybersecurity. Recently, we added to this list by showing how a machine learning algorithm (a so-called learner) combined with an optimization routine can assist experimental efforts in the realm of tuning semiconductor quantum dot (QD) devices. Among other applications, semiconductor quantum dots are a candidate system for building quantum computers. In order to employ QDs, one needs to tune the devices into a desirable configuration suitable for quantum computing. While current experiments adjust the control parameters heuristically, such an approach does not scale with the increasing size of the quantum dot arrays required for even near-term quantum computing demonstrations. Establishing a reliable protocol for tuning QD devices that does not rely on the gross-scale heuristics developed by experimentalists is thus of great importance.Materials and methodsTo implement the machine learning-based approach, we constructed a dataset of simulated QD device characteristics, such as the conductance and the charge sensor response versus the applied electrostatic gate voltages. The gate voltages are the experimental ‘knobs’ for tuning the device into useful regimes. Here, we describe the methodology for generating the dataset, as well as its validation in training convolutional neural networks.Results and discussionFrom 200 training sets sampled randomly from the full dataset, we show that the learner’s accuracy in recognizing the state of a device is ≈ 96.5% when using either current-based or charge-sensor-based training. The spread in accuracy over our 200 training sets is 0.5% and 1.8% for current- and charge-sensor-based data, respectively. In addition, we also introduce a tool that enables other researchers to use this approach for further research: QFlow lite—a Python-based mini-software suite that uses the dataset to train neural networks to recognize the state of a device and differentiate between states in experimental data. This work gives the definitive reference for the new dataset that will help enable researchers to use it in their experiments or to develop new machine learning approaches and concepts.

Autotuning of Double-Dot Devices In Situ with Machine Learning

“…In particular, we use a pre-trained CNN to determine the current global state of the device. To prepare the CNN, we rely on a dataset of 1001 quantum dot devices generated using a modified Thomas-Fermi approximation to model a set of reference semiconductor systems comprising of a quasi-1D nanowire with a series of depletion gates whose voltages determine the number of dots, the charges on each of those dots, and the conductance through the wire [26,27]. The dataset has been constructed to be agnostic about the details of a particular geometry and material platform used for fabricating dots.…”

“…The model used to simulate the QD devices [27] does not account for noise present in a real measurement. As a result, data used to train the CNN classifier obtained by taking a numerical gradient of the sensor data leads to very clean data, with the background uniformly flattened and charge transition lines clearly visible (see the first column in Fig.…”

Theoretical Bounds on Data Requirements for the Ray-Based Classification

“…and testing runs was reported [40]. More recently, the RBC has been verified using experimental data, both off-line (i.e., by sampling rays from pre-measured large 2D scans) and on-line (i.e., by directly measuring the device response in a ray-based fashion) [2].…”

Deep reinforcement learning for efficient measurement of quantum devices

“…However, quantum dot devices are subject to variability, and many measurements are required to characterise each device and find the conditions for qubit operation. Machine learning has been used to automate the tuning of devices from scratch, known as super coarse tuning [34][35][36] , the identification of single or double quantum dot regimes, known as coarse tuning 37,38 , and the tuning of the inter-dot tunnel couplings and other device parameters, referred to as fine tuning [39][40][41] .…”

“…We have previously developed an efficient measurement algorithm for quantum dot devices combining a deep-generative model and an informationtheoretic approach 42 . Other approaches have developed classification tools that are used in conjunction with numerical optimisation routines to navigate quantum dot current maps 37,40,43 . These methods, however, fail when there are large areas in parameter space that do not exhibit transport features.…”