Quantum process tomography of structured optical gates with convolutional neural networks

The characterization of a unitary gate is experimentally accomplished via Quantum Process Tomography, which combines the outcomes of different projective measurements to reconstruct the underlying operator. The process matrix is typically extracted from maximum-likelihood estimation. Recently, optimization strategies based on evolutionary and machine-learning techniques have been proposed. Here, we investigate a deep-learning approach that allows for fast and accurate reconstructions of space-dependent SU(2) operators, only processing a minimal set of measurements. We train a convolutional neural network based on a scalable U-Net architecture to process entire experimental images in parallel. Synthetic processes are reconstructed with average fidelity above 90%. The performance of our routine is experimentally validated on complex polarization transformations. Our approach further expands the toolbox of data-driven approaches to Quantum Process Tomography and shows promise in the real-time characterization of complex optical gates.