Machine-learning-assisted correction of correlated qubit errors in a topological code

Abstract

A fault-tolerant quantum computation requires an efficient means to detect and correct errors that accumulate in encoded quantum information. In the context of machine learning, neural networks are a promising new approach to quantum error correction. Here we show that a recurrent neural network can be trained, using only experimentally accessible data, to detect errors in a widely used topological code, the surface code, with a performance above that of the established minimum-weight perfect matching (or blossom) decoder. The performance gain is achieved because the neural network decoder can detect correlations between bit-flip (X) and phase-flip (Z) errors. The machine learning algorithm adapts to the physical system, hence no noise model is needed. The long short-term memory layers of the recurrent neural network maintain their performance over a large number of quantum error correction cycles, making it a practical decoder for forthcoming experimental realizations of the surface code.

arXiv comment10 pages, 5 figures; V3: version accepted by Quantum

References in corpus (33)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Fault-tolerant quantum computation by anyons
• Improving neural networks by preventing co-adaptation of feature detectors
• Surface codes: Towards practical large-scale quantum computation
• Recurrent Neural Network Regularization
• Topological quantum memory
• Quantum Error Correction for Quantum Memories
• Multiple Particle Interference and Quantum Error Correction
• State preservation by repetitive error detection in a superconducting quantum circuit
• Stabilizer Codes and Quantum Error Correction
• Surface code quantum computing by lattice surgery
• Quantum codes on a lattice with boundary
• Quantum computing with nearest neighbor interactions and error rates over 1%
• Low-distance Surface Codes under Realistic Quantum Noise
• Quantum Error Correction
• Fast Decoders for Topological Quantum Codes
• Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
• Towards practical classical processing for the surface code
• Demonstration of weight-four parity measurements in the surface code architecture
• Scalable quantum circuit and control for a superconducting surface code
• A Neural Decoder for Topological Codes
• Optimal Resources for Topological 2D Stabilizer Codes: Comparative Study
• Decoding Small Surface Codes with Feedforward Neural Networks
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• Density-matrix simulation of small surface codes under current and projected experimental noise
• An efficient Markov chain Monte Carlo algorithm for the surface code
• NP-hardness of decoding quantum error-correction codes
• Multi-path Summation for Decoding 2D Topological Codes
• Optimal complexity correction of correlated errors in the surface code
• A decoding algorithm for CSS codes using the X/Z correlations
• A proposal for a minimal surface code experiment
• Error correcting power of small topological codes

Cited by in corpus (83)

• Machine learning and the physical sciences
• Interfacing spin qubits in quantum dots and donors - hot, dense and coherent
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Ultrahigh Error Threshold for Surface Codes with Biased Noise
• Experimental quantum speed-up in reinforcement learning agents
• Artificial Intelligence and Machine Learning for Quantum Technologies
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• Neural Belief-Propagation Decoders for Quantum Error-Correcting Codes
• Quantum error correction for the toric code using deep reinforcement learning
• Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations
• Deep neural decoders for near term fault-tolerant experiments
• Measurement Based Feedback Quantum Control With Deep Reinforcement Learning for Double-well Non-linear Potential
• Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
• Improved decoding of circuit noise and fragile boundaries of tailored surface codes
• Quantum circuit optimization with deep reinforcement learning
• Advantages of versatile neural-network decoding for topological codes
• Neural-Network Decoders for Quantum Error Correction using Surface Codes:A Space Exploration of the Hardware Cost-Performance Trade-Offs
• Comparing neural network based decoders for the surface code
• Benchmarking Coherent Errors in Controlled-Phase Gates due to Spectator Qubits
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Learning quantum data with the quantum Earth Mover's distance
• Neural network decoder for topological color codes with circuit level noise
• Probing context-dependent errors in quantum processors
• Neural-network quantum state tomography
• Analysing correlated noise on the surface code using adaptive decoding algorithms
• Scalable Neural Network Decoders for Higher Dimensional Quantum Codes
• Machine learning assisted readout of trapped-ion qubits
• Machine learning \& artificial intelligence in the quantum domain
• Beyond Quantum Noise Spectroscopy: modelling and mitigating noise with quantum feature engineering
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Artificial Intelligence for Quantum Computing
• Neural-Network Decoders for Measurement Induced Phase Transitions
• Linear-time general decoding algorithm for the surface code
• Reinforcement learning for optimal error correction of toric codes
• Fault-tolerant Quantum Error Correction on Near-term Quantum Processors using Flag and Bridge Qubits
• Neural Network Decoders for Large-Distance 2D Toric Codes
• Unsupervised learning using topological data augmentation
• Deep Q-learning decoder for depolarizing noise on the toric code
• General framework for constructing fast and near-optimal machine-learning-based decoder of the topological stabilizer codes
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Machine Learning and Quantum Devices
• General tensor network decoding of 2D Pauli codes
• Modeling and Control of a Reconfigurable Photonic Circuit using Deep Learning
• Neural ensemble decoding for topological quantum error-correcting codes
• Correcting non-independent and non-identically distributed errors with surface codes
• Quantum variational learning for quantum error-correcting codes
• Designing quantum many-body matter with conditional generative adversarial networks
• Reducing the error rate of a superconducting logical qubit using analog readout information
• Cosmic-ray-induced correlated errors in superconducting qubit array
• Neural-network approach for identifying nonclassicality from click-counting data
• Determination of the Semion Code Threshold using Neural Decoders
• Convolutional neural network based decoders for surface codes
• A Scalable Decoder Micro-architecture for Fault-Tolerant Quantum Computing
• Data-driven decoding of quantum error correcting codes using graph neural networks
• Non-Markovian feedback for optimized quantum error correction
• Neural network decoder for near-term surface-code experiments
• Classification and reconstruction of optical quantum states with deep neural networks
• Experimental graybox quantum system identification and control
• Artificial Neural Network Syndrome Decoding on IBM Quantum Processors
• Quantum error reduction with deep neural network applied at the post-processing stage
• On maximum-likelihood decoding with circuit-level errors
• Machine-learning based noise characterization and correction on neutral atoms NISQ devices
• Error-rate-agnostic decoding of topological stabilizer codes
• An RNN-policy gradient approach for quantum architecture search
• Simulation of the five-qubit quantum error correction code on superconducting qubits
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Low-overhead quantum error correction codes with a cyclic topology
• Quantum error mitigation in the regime of high noise using deep neural network: Trotterized dynamics
• Decoherence and Quantum Error Correction for Quantum Computing and Communications
• A NEAT Quantum Error Decoder
• Wildcard error: Quantifying unmodeled errors in quantum processors
• Synergy between noisy quantum computers and scalable classical deep learning
• Introduction to Quantum Error Correction with Stabilizer Codes
• Efficient Syndrome Decoder for Heavy Hexagonal QECC via Machine Learning
• GAN decoder on a quantum toric code for noise-robust quantum teleportation
• Self-attention U-Net decoder for toric codes
• Efficient Decoding of Surface Code Syndromes for Error Correction in Quantum Computing
• Neural Decoders for Universal Quantum Algorithms
• On the interpretability of neural network decoders
• Mapping Surface Code to Superconducting Quantum Processors
• Challenges and opportunities in the supervised learning of quantum circuit outputs
• Subsystem many-hypercube codes: High-rate concatenated codes with low-weight syndrome measurements