Machine learning classification of non-Markovian noise disturbing quantum dynamics
arXiv:2101.03221 · doi:10.1088/1402-4896/acb39b
Abstract
In this paper machine learning and artificial neural network models are proposed for the classification of external noise sources affecting a given quantum dynamics. For this purpose, we train and then validate support vector machine, multi-layer perceptron and recurrent neural network models with different complexity and accuracy, to solve supervised binary classification problems. As a result, we demonstrate the high efficacy of such tools in classifying noisy quantum dynamics using simulated data sets from different realizations of the quantum system dynamics. In addition, we show that for a successful classification one just needs to measure, in a sequence of discrete time instants, the probabilities that the analysed quantum system is in one of the allowed positions or energy configurations. Albeit the training of machine learning models is here performed on synthetic data, our approach is expected to find application in experimental schemes, as e.g. for the noise benchmarking of noisy intermediate-scale quantum devices.
arXiv comment19 pages, 3 figures, 3 tables; v3: Changed title and improved presentation of the results
References in corpus (61)
- Adam: A Method for Stochastic Optimization
- Deep Learning in Neural Networks: An Overview
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Quantum Computing in the NISQ era and beyond
- Practical Bayesian Optimization of Machine Learning Algorithms
- Quantum sensing
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Attention-Based Models for Speech Recognition
- Non-Markovian dynamics in open quantum systems
- Quantum random walks - an introductory overview
- Sequence Transduction with Recurrent Neural Networks
- Quantum Non-Markovianity: Characterization, Quantification and Detection
- Quantum walks: a comprehensive review
- Dynamical decoupling and noise spectroscopy with a superconducting flux qubit
- Tune: A Research Platform for Distributed Model Selection and Training
- Quantum transport simulations in a programmable nanophotonic processor
- Non-Markovian quantum processes: complete framework and efficient characterisation
- Quantum channels and memory effects
- Dynamical decoupling noise spectroscopy
- Efficient learning of quantum noise
- Quantum stochastic processes and quantum non-Markovian phenomena
- Qubit noise spectroscopy for non-Gaussian dephasing environments
- Measurement of the Noise Spectrum Using a Multiple-Pulse Sequence
- Environmental noise spectroscopy with qubits subjected to dynamical decoupling
- A General Transfer-Function Approach to Noise Filtering in Open-Loop Quantum Control
- Programmable linear quantum networks with a multimode fibre
- Machine learning non-Markovian quantum dynamics
- Scanning Quantum Decoherence Microscopy
- Non-Gaussian noise spectroscopy with a superconducting qubit sensor
- Two-qubit spectroscopy of spatiotemporally correlated quantum noise in superconducting qubits
- Optimal control for one-qubit quantum sensing
- The effect of noise correlations on randomized benchmarking
- Application of optimal band-limited control protocols to quantum noise sensing
- Determining the Quantum Expectation Value by Measuring a Single Photon
- Reconfigurable optical implementation of quantum complex networks
- Dynamical decoupling noise spectroscopy at an optimal working point of a qubit
- Using deep learning to understand and mitigate the qubit noise environment
- Quantum diffusion with disorder, noise and interaction
- Experimental test of exchange fluctuation relations in an open quantum system
- Zeno and anti-Zeno effects for photon polarization dephasing
- Witnessing quantum memory in non-Markovian processes
- Beyond Quantum Noise Spectroscopy: modelling and mitigating noise with quantum feature engineering
- Noise spectroscopy of a quantum-classical environment with a diamond qubit
- Randomized benchmarking for non-Markovian noise
- Simultaneous spectral estimation of dephasing and amplitude noise on a qubit sensor via optimally band-limited control
- Estimating the degree of non-Markovianity using machine learning
- Experimental proof of Quantum Zeno-assisted Noise Sensing
- Extending comb-based spectral estimation to multiaxis quantum noise
- Quantum Zeno and Anti-Zeno probes of noise correlations in photon polarisation
- Noise-robust quantum sensing via optimal multi-probe spectroscopy
- The dynamical-decoupling-based spatiotemporal noise spectroscopy
- Stochastic quantum Zeno-based detection of noise correlations
- Noise Sensing via Stochastic Quantum Zeno
- Classification of cancer pathology reports: a large-scale comparative study
- Disorder and dephasing as control knobs for light transport in optical fiber cavity networks
- Non-Markovian memory in IBMQX4
- Transfer-tensor description of memory effects in open-system dynamics and multi-time statistics
- Quantum State Discrimination on Reconfigurable Noise-Robust Quantum Networks
- Noise fingerprints in quantum computers: Machine learning software tools
- Role of the filter functions in noise spectroscopy
Cited by in corpus (7)
- Quantum-Noise-Driven Generative Diffusion Models
- Spectral Density Classification For Environment Spectroscopy
- Noise Detection with Spectator Qubits and Quantum Feature Engineering
- The role of data embedding in equivariant quantum convolutional neural networks
- Machine-learning based noise characterization and correction on neutral atoms NISQ devices
- A machine learning based approach to the identification of spectral densities in quantum open systems
- Detecting Markovianity of Quantum Processes via Recurrent Neural Networks