We build a general quantum state tomography framework that makes use of machine learning techniques to reconstruct quantum states from a given set of coincidence measurements. For a wide range of pure and mixed input states we demonstrate via simulations that our method produces functionally equivalent reconstructed states to that of traditional methods with the added benefit that expensive computations are front-loaded with our system. Further, by training our system with measurement results that include simulated noise sources we are able to demonstrate a significantly enhanced average fidelity when compared to typical reconstruction methods. These enhancements in average fidelity are also shown to persist when we consider state reconstruction from partial tomography data where several measurements are missing.

We develop a state-of-the-art generative neural network (GNN) and convolutional neural network (CNN) system in combination, and demonstrate its efficacy in simulated and experimental communications settings. Experimentally, the GNN system corrects for distortion and reduces detector noise, resulting in nearly identical-to-desired mode profiles at the receiver, requiring no feedback or adaptive optics. Classification accuracy is significantly improved when these generated modes are demodulated using a CNN that is pre-trained with undistorted modes. Using the GNN and CNN system exclusively pre-trained with simulated optical profiles, we show a reduction in cross-talk between experimentally-detected noisy/distorted modes at the receiver. This scalable scheme may provide a concrete and effective demodulation technique for establishing long-range classical and quantum communication links. 

Accuracy in discriminating between different received coherent signals is integral to the operation of many free-space communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communication scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we design the neural network system such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is distributed to the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. 

We design an optical feedback network making use of machine learning techniques and demonstrate via simulations its ability to correct for the effects of turbulent propagation on optical modes. This artificial neural network scheme only relies on measuring the intensity profile of the distorted modes, making the approach simple and robust. The network results in the generation of various mode profiles at the transmitter that, after propagation through turbulence, closely resemble the desired target mode. The corrected optical mode profiles at the receiver are found to be nearly identical to the desired profiles, with near-zero mean square error indices. 

In this article, the self‐learning and self‐evolving features of artificial neural networks are exploited to correct the complex spatial profile of distorted Laguerre–Gaussian modes at the single‐photon level. Furthermore, the potential of this technique is used to improve the channel capacity of an optical communication protocol that relies on structured single photons. The results have important implications for real‐time turbulence correction of structured photons and single‐photon images. 

In this work we demonstrate the efficacy of neural networks in the characterization of dispersive media. We also develop a neural network to make predictions for input probe pulses which propagate through a nonlinear dispersive medium, which may be applied to predicting optimal pulse shapes for a desired output. The setup requires only a single pulse for the probe, providing considerable simplification of the current method of dispersion characterization that requires frequency scanning across the entirety of the gain and absorption features. We show that the trained networks are able to predict pulse profiles as well as dispersive features that are nearly identical to their experimental counterparts. 

we demonstrate the ability of deep neural networks to classify numerically generated, noisy Laguerre–Gauss modes of up to 100 quanta of orbital angular momentum with near-unity fidelity.  The scheme relies only on the intensity profile of the detected modes, allowing for considerable simplification of current measurement schemes required to sort the states containing increasing degrees of orbital angular momentum. We also present results that show the strength of deep neural networks in the classification of experimental superpositions of Laguerre–Gauss modes when the networks are trained solely using simulated images