Autotuning of Double-Dot Devices 
<i>In Situ</i>
 with Machine Learning

Zwolak, Justyna P.; McJunkin, Thomas; Kalantre, Sandesh S.; Dodson, J. P.; MacQuarrie, E. R.; Savage, D. E.; Lagally, M. G.; Coppersmith, S. N.; Eriksson, M. A.; Taylor, Jacob M.

doi:10.1103/physrevapplied.13.034075

Cited by 55 publications

(49 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the transport features that indicate the device is tuned as a double quantum dot are time-consuming to measure and difficult to parametrise. Machine learning techniques and other automated approaches have been used for tuning quantum devices [5][6][7][8][9][10][11][12][13][14] . These techniques are limited to small regions of the device parameter space or require information about the device characteristics.…”

mentioning

confidence: 99%

Machine learning enables completely automatic tuning of a quantum device faster than human experts

et al. 2020

View full text Add to dashboard Cite

Variability is a problem for the scalability of semiconductor quantum devices. The parameter space is large, and the operating range is small. Our statistical tuning algorithm searches for specific electron transport features in gate-defined quantum dot devices with a gate voltage space of up to eight dimensions. Starting from the full range of each gate voltage, our machine learning algorithm can tune each device to optimal performance in a median time of under 70 minutes. This performance surpassed our best human benchmark (although both human and machine performance can be improved). The algorithm is approximately 180 times faster than an automated random search of the parameter space, and is suitable for different material systems and device architectures. Our results yield a quantitative measurement of device variability, from one device to another and after thermal cycling. Our machine learning algorithm can be extended to higher dimensions and other technologies.

show abstract

mentioning

confidence: 99%

Machine learning enables completely automatic tuning of a quantum device faster than human experts

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To further illustrate the advantages of our algorithm, we compared its performance with a Nelder-Mead numerical optimisation method applied to achieve automatic tuning of quantum dots 38,43 . To ensure a fair comparison with our reinforcement-learning method, our implementation of the Nelder-Mead optimisation (see Supplementary Note E. for further details) was terminated when the CNN classified a block as exhibiting bias triangles in the same way as our DRL algorithm, i.e., when the output value of the CNN classifier was >0.5.…”

Section: Resultsmentioning

confidence: 99%

“…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] .…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning for efficient measurement of quantum devices

et al. 2021

View full text Add to dashboard Cite

Deep reinforcement learning is an emerging machine-learning approach that can teach a computer to learn from their actions and rewards similar to the way humans learn from experience. It offers many advantages in automating decision processes to navigate large parameter spaces. This paper proposes an approach to the efficient measurement of quantum devices based on deep reinforcement learning. We focus on double quantum dot devices, demonstrating the fully automatic identification of specific transport features called bias triangles. Measurements targeting these features are difficult to automate, since bias triangles are found in otherwise featureless regions of the parameter space. Our algorithm identifies bias triangles in a mean time of <30 min, and sometimes as little as 1 min. This approach, based on dueling deep Q-networks, can be adapted to a broad range of devices and target transport features. This is a crucial demonstration of the utility of deep reinforcement learning for decision making in the measurement and operation of quantum devices.

show abstract

“…Here, we report on the performance of neural networks, which have been previously used to tune the electrostatics of devices 15 – 18 , to post-process single spin readout by spin-to-charge conversion. We compare their robustness and post-processing time to a Bayesian inference filter.…”

Section: Introductionmentioning

confidence: 99%

Robust and fast post-processing of single-shot spin qubit detection events with a neural network

Struck

Lindner

Hollmann

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Establishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

show abstract

Autotuning of Double-Dot Devices In Situ with Machine Learning

Cited by 55 publications

References 29 publications

Machine learning enables completely automatic tuning of a quantum device faster than human experts

Machine learning enables completely automatic tuning of a quantum device faster than human experts

Deep reinforcement learning for efficient measurement of quantum devices

Robust and fast post-processing of single-shot spin qubit detection events with a neural network

Contact Info

Product

Resources

About