Random telegraph signal analysis with a recurrent neural network
arXiv:2002.05817 · doi:10.1103/PhysRevE.102.012312
Abstract
We use an artificial neural network to analyze asymmetric noisy random telegraph signals (RTSs), and extract underlying transition rates. We demonstrate that a long short-term memory neural network can vastly outperform conventional methods, particularly for noisy signals. Our technique gives reliable results as the signal-to-noise ratio approaches one, and over a wide range of underlying transition rates. We apply our method to random telegraph signals generated by a superconducting double dot based photon detector, allowing us to extend our measurement of quasiparticle dynamics to new temperature regimes.
arXiv comment5 pages, 5 figures
References in corpus (17)
- Deep Learning in Neural Networks: An Overview
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Reinforcement Learning with Neural Networks for Quantum Feedback
- Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
- Machine Learning techniques for state recognition and auto-tuning in quantum dots
- Kinetics of non-equilibrium quasiparticle tunneling in superconducting charge qubits
- Quasiparticle decay rate of Josephson charge qubit oscillations
- Poisson transition rates from time-domain measurements with finite bandwidth
- Optical detection of single electron transport dynamics
- Microsecond resolution of quasiparticle tunneling in the single-Cooper-pair-transistor
- Time-domain measurements of quasiparticle tunneling rates in a single-Cooper-pair transistor
- Atomic-level Characterisation of Quantum Computer Arrays by Machine Learning
- Time-resolved charge detection with cross-correlation techniques
- Identifying single electron charge sensor events using wavelet edge detection
- Splitting a single Cooper-pair with microwave light
- Determining the parameters of a random telegraph signal by digital low pass filtering
- Cooper pair tunnelling and quasiparticle poisoning in a galvanically isolated superconducting double dot