Improved Tomographic Estimates by Specialised Neural Networks
arXiv:2211.11655 · doi:10.1002/qute.202300027
Abstract
Characterization of quantum objects, being them states, processes, or measurements, complemented by previous knowledge about them is a valuable approach, especially as it leads to routine procedures for real-life components. To this end, Machine Learning algorithms have demonstrated to successfully operate in presence of noise, especially for estimating specific physical parameters. Here we show that a neural network (NN) can improve the tomographic estimate of parameters by including a convolutional stage. We applied our technique to quantum process tomography for the characterization of several quantum channels. We demonstrate that a stable and reliable operation is achievable by training the network only with simulated data. The obtained results show the viability of this approach as an effective tool based on a completely new paradigm for the employment of NNs operating on classical data produced by quantum systems.
References in corpus (43)
- On the Measurement of Qubits
- Many-body quantum state tomography with neural networks
- Witnessing multipartite entanglement
- Quantum Process Tomography: Resource Analysis of Different Strategies
- Ancilla-assisted quantum process tomography
- Iterative maximum-likelihood reconstruction in quantum homodyne tomography
- Active learning machine learns to create new quantum experiments
- Detection of entanglement with few local measurements
- Automated Search for new Quantum Experiments
- Machine Learning for Precise Quantum Measurement
- Experimental Detection of Entanglement with Polarized Photons
- Experimental Bayesian Quantum Phase Estimation on a Silicon Photonic Chip
- Optimized quantum sensing with a single electron spin using real-time adaptive measurements
- Experimental neural network enhanced quantum tomography
- Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
- Experimental Machine Learning of Quantum States
- Machine learning-based classification of vector vortex beams
- Integrating Neural Networks with a Quantum Simulator for State Reconstruction
- Measuring Controlled-NOT and two-qubit gate operation
- Machine learning method for state preparation and gate synthesis on photonic quantum computers
- Control-enhanced multiparameter quantum estimation
- An Efficient Algorithm for Optimizing Adaptive Quantum Metrology Processes
- Learning in Quantum Control: High-Dimensional Global Optimization for Noisy Quantum Dynamics
- Experimental Phase Estimation Enhanced By Machine Learning
- Computer-inspired concept for high-dimensional multipartite quantum gates
- Efficient quantum state tomography with convolutional neural networks
- Experimental demonstration of a Hadamard gate for coherent state qubits
- Differential Evolution for Many-Particle Adaptive Quantum Metrology
- Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
- Experimental quantum homodyne tomography via machine learning
- Production of photonic universal quantum gates enhanced by machine learning
- Experimental Realization of Optimal Noise Estimation for a General Pauli Channel
- Calibration of quantum sensors by neural networks
- A search algorithm for quantum state engineering and metrology
- Bayesian estimation for quantum sensing in the absence of single-shot detection
- Robust calibration of multiparameter sensors via machine learning at the single-photon level
- Designing quantum experiments with a genetic algorithm
- Simplified Quantum Process Tomography
- Neural networks for detecting multimode Wigner-negativity
- Robustness of Quantum-Enhanced Adaptive Phase Estimation
- Quantum process tomography of a controlled-phase gate for time-bin qubits
- Feedback Ansatz for Adaptive-Feedback Quantum Metrology Training with Machine Learning
- Neural-network approach for identifying nonclassicality from click-counting data