Machine-learning-assisted electron-spin readout of nitrogen-vacancy center in diamond

Abstract

Machine learning is a powerful tool in finding hidden data patterns for quantum information processing. Here, we introduce this method into the optical readout of electron-spin states in diamond via single-photon collection and demonstrate improved readout precision at room temperature. The traditional method of summing photon counts in a time gate loses all the timing information crudely. We find that changing the gate width can only optimize the contrast or the state variance, not both. In comparison, machine learning adaptively learns from time-resolved fluorescence data and offers the optimal data processing model that elaborately weights each time bin to maximize the extracted information. It is shown that our method can repair the processing result from imperfect data, reducing 7% in spin readout error while optimizing the contrast. Note that these improvements only involve recording photon time traces and consume no additional experimental time, and they are, thus, robust and free. Our machine learning method implies a wide range of applications in the precision measurement and optical detection of states.

Mie Sensing with Neural Networks: Recognition of Nano‐Object Parameters, the Invisibility Point, and Restricted Models

“…In particular, the ML ideology was successfully applied in several experimental reports on photonic metamaterials: refs. [19,22,24,31,61,62]. One of the goals of this paper is to motivate experimental work in electromagnetic Mie sensing.…”

“…Those parameters can be, e.g., nanostructure dimension, [25,26,29] morphology [30] and shape, [23] or chiral nano-object design. [27][28][29] Nonetheless, there are notable works showing interest in performing classification tasks in nanophotonics, e.g., the optical recording of electron-spin states in diamond via single-photon collection, [31] strengthening readout in high-density data storage, [19] or the label-free identification of pathogenic bacteria [24] and cells. [32] The inverse problem can also be addressed through a mixed approach, e.g., when the physical dimensions of nano-objects are predicted by regression, while their material is labeled and classified.…”

Frequentist Parameter Estimation with Supervised Learning

“…The training set contains Mj = 2 × 10 3 feature vectors at each grid point (on average) and during training we use a mini-batch size of 256 with 75 training epochs, which ensures the cost saturates the phase-averaged CRB Eq. (18). models Θ W until the phase-averaged CRB is saturated, and compare the mean (solid blue) and standard deviation (shaded gray region) to the MLE (dashed orange).…”

“…Quantum parameter estimation is an active area of research, which has both fascinating implications for fundamental science and applications in state-of-the art quantum sensors [1,2]. Like many areas of quantum science, quantum parameter estimation can potentially benefit from the application of machine learning techniques [3,4,29], in particular adaptive Bayesian schemes [5][6][7][8][9][10][11][12][13][14], improved readout in noisy single-qubit magnetometers [15][16][17][18][19] and state preparation [20,21]. Although current efforts to improve the sensitivity and utility of quantum sensors is focused on the use of non-classical states [1], the development of sophisticated data analysis techniques to extract information encoded in complex quantum states is also an important aspect of this effort.…”

Feedforward Quantum Control and Coherence Protection of Single Electron Spin in Diamond using Deep Learning

“…Machine learning is a group of methods that are well developed in computer science and has been applied in quantum control fields including Hamilto-nian learning [14], qubit readout [15][16][17][18][19] and experimental controls [20,21]. Recently, the deep learning model (DL) [22] is emerging as a powerful tool, which can deal with complicated problems with multiple layers of artificial neural network such as the many-body problem [23].…”