Machine Learning techniques for state recognition and auto-tuning in quantum dots

Abstract

Recent progress in building large-scale quantum devices for exploring quantum computing and simulation paradigms has relied upon effective tools for achieving and maintaining good experimental parameters, i.e. tuning up devices. In many cases, including in quantum-dot based architectures, the parameter space grows substantially with the number of qubits, and may become a limit to scalability. Fortunately, machine learning techniques for pattern recognition and image classification using so-called deep neural networks have shown surprising successes for computer-aided understanding of complex systems. In this work, we use deep and convolutional neural networks to characterize states and charge configurations of semiconductor quantum dot arrays when one can only measure a current-voltage characteristic of transport (here conductance) through such a device. For simplicity, we model a semiconductor nanowire connected to leads and capacitively coupled to depletion gates using the Thomas-Fermi approximation and Coulomb blockade physics. We then generate labelled training data for the neural networks, and find at least $90\%$ accuracy for charge and state identification for single and double dots purely from the dependence of the nanowire's conductance upon gate voltages. Using these characterization networks, we can then optimize the parameter space to achieve a desired configuration of the array, a technique we call `auto-tuning'. Finally, we show how such techniques can be implemented in an experimental setting by applying our approach to an experimental data set, and outline further problems in this domain, from using charge sensing data to extensions to full one and two-dimensional arrays, that can be tackled with machine learning.

15 pages, 10 figures

References in corpus (12)

• Improving neural networks by preventing co-adaptation of feature detectors
• Probing many-body dynamics on a 51-atom quantum simulator
• A programmable two-qubit quantum processor in silicon
• A blueprint for demonstrating quantum supremacy with superconducting qubits
• Scalable gate architecture for densely packed semiconductor spin qubits
• A Crossbar Network for Silicon Quantum Dot Qubits
• Assessing the progress of trapped-ion processors towards fault-tolerant quantum computation
• Integrated silicon qubit platform with single-spin addressability, exchange control and robust single-shot singlet-triplet readout
• Sideband cooling and coherent dynamics in a microchip multi-segmented ion trap
• Tuning methods for semiconductor spin--qubits
• Full control of quadruple quantum dot circuit charge states in the single electron regime
• Symmetric Operation of the Resonant Exchange Qubit

Cited by in corpus (59)

• Machine learning and the physical sciences
• Quantum Dot Arrays in Silicon and Germanium
• Machine learning enables completely automatic tuning of a quantum device faster than human experts
• Machine learning assisted quantum state estimation
• Auto-tuning of double dot devices in situ with machine learning
• Automated tuning of double quantum dots into specific charge states using neural networks
• Colloquium: Advances in automation of quantum dot devices control
• Efficiently measuring a quantum device using machine learning
• Computer-automated tuning procedures for semiconductor quantum dot arrays
• Quantum machine learning and quantum biomimetics: A perspective
• Autonomous tuning and charge state detection of gate defined quantum dots
• A Machine Learning Approach for Automated Fine-Tuning of Semiconductor Spin Qubits
• Artificial Intelligence for Quantum Computing
• QFlow lite dataset: A machine-learning approach to the charge states in quantum dot experiments
• Applying machine learning optimization methods to the production of a quantum gas
• Finite-key analysis for twin-field quantum key distribution with composable security
• Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
• Scalable Hamiltonian learning for large-scale out-of-equilibrium quantum dynamics
• Toward Robust Autotuning of Noisy Quantum Dot Devices
• Algorithm for automated tuning of a quantum dot into the single-electron regime
• Ray-based framework for state identification in quantum dot devices
• Machine-learning enhanced dark soliton detection in Bose-Einstein condensates
• Miniaturizing neural networks for charge state autotuning in quantum dots
• Tuning arrays with rays: Physics-informed tuning of quantum dot charge states
• CMOS Quantum Computing: Toward A Quantum Computer System-on-Chip
• Autonomous estimation of high-dimensional Coulomb diamonds from sparse measurements
• An automated approach for consecutive tuning of quantum dot arrays
• Robust and fast post-processing of single-shot spin qubit detection events with a neural network
• Scalable on-chip multiplexing of silicon single and double quantum dots
• Machine learning optimization of Majorana hybrid nanowires
• Machine Learning-Assisted Manipulation and Readout of Molecular Spin Qubits
• Quantum error reduction with deep neural network applied at the post-processing stage
• Cross-architecture Tuning of Silicon and SiGe-based Quantum Devices Using Machine Learning
• Data needs and challenges for quantum dot devices automation
• Identifying Pauli spin blockade using deep learning
• Modular Autonomous Virtualization System for Two-Dimensional Semiconductor Quantum Dot Arrays
• Estimation of Convex Polytopes for Automatic Discovery of Charge State Transitions in Quantum Dot Arrays
• Automatic virtual voltage extraction of a 2x2 array of quantum dots with machine learning
• Fully autonomous tuning of a spin qubit
• Theoretical bounds on data requirements for the ray-based classification
• Quantum reinforcement learning in the presence of thermal dissipation
• Random telegraph signal analysis with a recurrent neural network
• Quantum inspired qubit qutrit neural networks for real time financial forecasting
• Visual explanations of machine learning model estimating charge states in quantum dots
• Automation of Quantum Dot Measurement Analysis via Explainable Machine Learning
• Quantum error mitigation in the regime of high noise using deep neural network: Trotterized dynamics
• Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
• Ray-based classification framework for high-dimensional data
• Topological gap protocol based machine learning optimization of Majorana hybrid wires
• Simulation of Charge Stability Diagrams for Automated Tuning Solutions (SimCATS)
• Experimental online quantum dots charge autotuning using neural networks
• Preserving Coulomb blockade in transport spectroscopy of quantum dots, by dynamical tunnel-barrier compensation
• Robust quantum dots charge autotuning using neural network uncertainty
• Optimizing energy conversion with nonthermal resources in steady-state quantum devices
• QDsim: A user-friendly toolbox for simulating large-scale quantum dot devices
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• Automated in situ optimization and disorder mitigation in a quantum device
• Long-range spin transport in asymmetric quadruple quantum dots configurations
• QDFlow: A Python package for physics simulations of quantum dot devices