Visual explanations of machine learning model estimating charge states in quantum dots
arXiv:2210.15070 · doi:10.1063/5.0193621
Abstract
Charge state recognition in quantum dot devices is important in the preparation of quantum bits for quantum information processing. Toward auto-tuning of larger-scale quantum devices, automatic charge state recognition by machine learning has been demonstrated. For further development of this technology, an understanding of the operation of the machine learning model, which is usually a black box, will be useful. In this study, we analyze the explainability of the machine learning model estimating charge states in quantum dots by gradient-weighted class activation mapping, which identified class-discriminative regions for the predictions. The model predicts the state based on the change transition lines, indicating that human-like recognition is realized. We also demonstrate improvements of the model by utilizing feedback from the mapping results. Due to the simplicity of our simulation and pre-processing methods, our approach offers scalability without significant additional simulation costs, demonstrating its suitability for future quantum dot system expansions.
arXiv comment17 pages, 4 figures
References in corpus (41)
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Driven coherent oscillations of a single electron spin in a quantum dot
- An addressable quantum dot qubit with fault-tolerant control fidelity
- A Two Qubit Logic Gate in Silicon
- A >99.9%-fidelity quantum-dot spin qubit with coherence limited by charge noise
- A programmable two-qubit quantum processor in silicon
- Interfacing spin qubits in quantum dots and donors - hot, dense and coherent
- A CMOS silicon spin qubit
- Electrically driven single electron spin resonance in a slanting Zeeman field
- Computing with spin qubits at the surface code error threshold
- Fast universal quantum control above the fault-tolerance threshold in silicon
- Few-Electron Quantum Dot Circuit with Integrated Charge Read-Out
- Silicon CMOS architecture for a spin-based quantum computer
- Qubits made by advanced semiconductor manufacturing
- Fast Single-Charge Sensing with an rf Quantum Point Contact
- Precision tomography of a three-qubit donor quantum processor in silicon
- A fault-tolerant addressable spin qubit in a natural silicon quantum dot
- A hole spin qubit in a fin field-effect transistor above 4 kelvin
- Quantum error correction with silicon spin qubits
- Loading a quantum-dot based "Qubyte" register
- Machine Learning techniques for state recognition and auto-tuning in quantum dots
- Fast Electrical Control of Single Electron Spins in Quantum Dots with Vanishing Influence from Nuclear Spins
- Machine learning enables completely automatic tuning of a quantum device faster than human experts
- Auto-tuning of double dot devices in situ with machine learning
- Automated tuning of inter-dot tunnel couplings in quantum dot arrays
- Automated tuning of double quantum dots into specific charge states using neural networks
- Computer-automated tuning of semiconductor double quantum dots into the single-electron regime
- 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
- Detection and control of charge states in a quintuple quantum dot
- Autonomous tuning and charge state detection of gate defined quantum dots
- A Machine Learning Approach for Automated Fine-Tuning of Semiconductor Spin Qubits
- Toward Robust Autotuning of Noisy Quantum Dot Devices
- Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
- Algorithm for automated tuning of a quantum dot into the single-electron regime
- Quantum device fine-tuning using unsupervised embedding learning
- Single-electron Spin Resonance in a Quadruple Quantum Dot
- An automated approach for consecutive tuning of quantum dot arrays
- Optimization of Quantum-dot Qubit Fabrication via Machine Learning
- Gate voltage dependence of noise distribution in radio-frequency reflectometry in gallium arsenide quantum dots