Recurrent neural network approach to quantum signal: coherent state restoration for continuous-variable quantum key distribution

Lu, Weizhao; Huang, Chunhui; Hou, Kun; Shi, Liting; Zhao, Huihui; Li, Zhengmei; Qiu, Jianfeng

doi:10.1007/s11128-018-1877-y

Cited by 13 publications

(32 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experimental setup, channel noise, measurement noise and other kind of noise produce a tremendous influence on coherent detection, so an efficient signal identification method should be applied in order to distinguish the quantum state correctly. In this study, we used the recurrent quantum neural network (RQNN) with Schrödinger equation for system control and coherent states extraction [33].…”

Section: Application In Optical Communication Systemmentioning

confidence: 99%

“…The receiving data was embedded with heavy noise, adjacent state could hardly be separated. At this time, RQNN approach was applied for signal restoration of the receiving signal [33]. And the signal after RQNN is shown in Figure 9c.…”

Section: B Performance Verification Of the Multiplexermentioning

confidence: 99%

“…, which represents the collective response of the neurons, evolves with the potential energy. By establishment of the potential energy through RQNN, coherent states could be accurately extracted from the noise [33].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Coherent Polarization States Multiplexer and Its Feasibility in Quantum Communication

Qiu

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In this paper, a multiplexing technique of coherent polarization states based on threedimensional rotation group is proposed. The technique applies two Stokes parameters in one polarized light as signal and local oscillator (LO), and combines them in the single spatial mode. Three-dimensional rotation group SO(3) is used to describe the transformation of Stokes parameters. SO(3) is decomposed into three subgroups, with each subgroup represents a rotation along different axes. A multiplexer is designed with three electro-optical crystals to realize the function of three-dimensional rotation group. The multiplexer achieves an ergodicity of polarization states. Signal and LO propagates in the same spatial mode, multiplexing of polarization states is realized. Finally, the multiplexer is tested in a free space quantum communication system and its feasibility in quantum communication is confirmed.

show abstract

Section: Application In Optical Communication Systemmentioning

confidence: 99%

Section: B Performance Verification Of the Multiplexermentioning

confidence: 99%

See 1 more Smart Citation

Coherent Polarization States Multiplexer and Its Feasibility in Quantum Communication

Qiu

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, there is recent literature that e.g. apply machine learning to continuous-variable (CV) QKD to improve the noise-filtering [14] and the prediction/compensation of intensity evolution of light over time [15], respectively.…”

Section: B Neural Networkmentioning

confidence: 99%

Machine learning for optimal parameter prediction in quantum key distribution

Wang

Lo²

2019

Phys. Rev. A

View full text Add to dashboard Cite

For a practical quantum key distribution (QKD) system, parameter optimization -the choice of intensities and probabilities of sending them -is a crucial step in gaining optimal performance, especially when one realistically considers finite communication time. With the increasing interest in the field to implement QKD over free-space on moving platforms, such as drones, handheld systems, and even satellites, one needs to perform parameter optimization with low latency and with very limited computing power. Moreover, with the advent of the Internet of Things (IoT), a highly attractive direction of QKD could be a quantum network with multiple devices and numerous connections, which provides a huge computational challenge for the controller that optimizes parameters for a large-scale network. Traditionally, such an optimization relies on brute-force search, or local search algorithms, which are computationally intensive, and will be slow on low-power platforms (which increases latency in the system) or infeasible for even moderately large networks. In this work we present a new method that uses a neural network to directly predict the optimal parameters for QKD systems. We test our machine learning algorithm on hardware devices including a Raspberry Pi 3 single-board-computer (similar devices are commonly used on drones) and a mobile phone, both of which have a power consumption of less than 5 watts, and we find a speedup of up to 100-1000 times when compared to standard local search algorithms. The predicted parameters are highly accurate and can preserve over 95-99% of the optimal secure key rate. Moreover, our approach is highly general and not limited to any specific QKD protocol. I. BACKGROUND A. Parameter Optimization in QKDQuantum key distribution (QKD)[1-4] provides unconditional security in generating a pair of secure key between two parties, Alice and Bob. To address imperfections in realistic source and detectors, decoy-state QKD [5][6][7] uses multiple intensities to estimate single-photon contributions, and allows the secure use of Weak Coherent Pulse (WCP) sources, while measurement-deviceindependent QKD (MDI-QKD) [8] addresses susceptibility of detectors to hacking by eliminating detector side channels and allowing Alice and Bob to send signals to an untrusted third party, Charles, who performs the measurement.In reality, a QKD experiment always has a limited transmission time, therefore the total number of signals is finite. This means that, when estimating the single-photon contributions with decoy-state analysis, one would need to take into consideration the statistical fluctuations of the observables: the Gain and Quantum Bit Error Rate (QBER). This is called the finite-key analysis of QKD. When considering finite-size effects, the choice of intensities and probabilities of sending these intensities is crucial to getting the optimal rate. Therefore, we would need to perform optimizations for the search of parameters.Traditionally, the optimization of parameters is implemented as either a brute-for...

show abstract

“…In this context, there are already several quantisations of RNNs [40][41][42][43][44], usually exploiting a substitution of the feed-forward NNs in RNNs, LSTMs or GRUs with some form of QNN. Typically such QNNs encode classical information into a quantum state, apply a variational circuit [37,[45][46][47][48][49] or a tunable evolution [44,[50][51][52][53][54][55], and then carry out a measurement, followed by further classical processing. A similar approach can be pursued with non-RNN variational classes used for machine learning with memory, such as matrix-product operators [56,57].…”

Section: Introductionmentioning

confidence: 99%

Learning Quantum Processes with Memory -- Quantum Recurrent Neural Networks

Bondarenko¹,

Salzmann²,

Schmiesing³

2023

Preprint

View full text Add to dashboard Cite

Recurrent neural networks play an important role in both research and industry. With the advent of quantum machine learning, the quantisation of recurrent neural networks has become recently relevant. We propose fully quantum recurrent neural networks, based on dissipative quantum neural networks, capable of learning general causal quantum automata. A quantum training algorithm is proposed and classical simulations for the case of product outputs with the fidelity as cost function are carried out. We thereby demonstrate the potential of these algorithms to learn complex quantum processes with memory in terms of the exemplary delay channel, the time evolution of quantum states governed by a time-dependent Hamiltonian, and highand low-frequency noise mitigation. Numerical simulations indicate that our quantum recurrent neural networks exhibit a striking ability to generalise from small training sets.

show abstract

Recurrent neural network approach to quantum signal: coherent state restoration for continuous-variable quantum key distribution

Cited by 13 publications

References 25 publications

Coherent Polarization States Multiplexer and Its Feasibility in Quantum Communication

Coherent Polarization States Multiplexer and Its Feasibility in Quantum Communication

Machine learning for optimal parameter prediction in quantum key distribution

Learning Quantum Processes with Memory -- Quantum Recurrent Neural Networks

Contact Info

Product

Resources

About