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

Abstract

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.

Fast high-fidelity single-shot readout of spins in silicon using a single-electron box

“…We note F M,JPA = 99% is already achieved at ∆t JPA = 131 µs. We further explore machine learning-based approaches to improve readout fidelity [30,31]. Here, by using Neural Networks, we report an increased fidelity of F M = 99.1% in ∆t = 500 µs, and F M,JPA = 99.54% in ∆t = 250 µs without and with a JPA respectively (See §XI for more information).…”

Learning Quantum Systems

“…Non-linear Bayesian filters have improved on threshold fidelities by considering the full time-resolved readout signal while accounting for relaxation [120] and stochastic turn-on times in spin-to-charge conversion readout [121]. NNs have improved on threshold methods in diamond NV centres, which lack single-shot readout at room temperature [119], and NN classifiers trained on synthetic time-resolved data have surpassed the performance of Bayesian filters in quantum-dot spin qubit readout [122]. Multi-qubit states have been classified using NNs in trapped-ion qubits, where time-binned multichannel data has provided the highest fidelity [123].…”

Threshold-independent method for single-shot readout of spin qubits in semiconductor quantum dots

“…Several methods have been developed to optimize the readout fidelity F R and visibility V R , as well as to find out the corresponding optimal threshold voltage x t and readout time t r , e.g., wavelet edge detection, [17] the analytical expres-sion of the distribution, [18,19] statistical techniques, [21] neural network, [20] digital processing, [22] and the Monte-Carlo method. [23] Among these methods, the Monte-Carlo method is now widely used to numerically simulate the distributions of the experimental data in Si-MOS QDs, [24] Si/SiGe QDs, [25] Ge QDs, [26] single donors, [27] and nitrogen-vacancy centers.…”