Convolutional neural network based decoders for surface codes
arXiv:2312.03508 · doi:10.1007/s11128-023-03898-2
Abstract
The decoding of error syndromes of surface codes with classical algorithms may slow down quantum computation. To overcome this problem it is possible to implement decoding algorithms based on artificial neural networks. This work reports a study of decoders based on convolutional neural networks, tested on different code distances and noise models. The results show that decoders based on convolutional neural networks have good performance and can adapt to different noise models. Moreover, explainable machine learning techniques have been applied to the neural network of the decoder to better understand the behaviour and errors of the algorithm, in order to produce a more robust and performing algorithm.
24 pages, 23 figures, 3 tables
References in corpus (27)
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Surface codes: Towards practical large-scale quantum computation
- Quantum Error Correction for Quantum Memories
- Object Detectors Emerge in Deep Scene CNNs
- Surface code quantum computing by lattice surgery
- Quantum Decoherence
- A Game of Surface Codes: Large-Scale Quantum Computing with Lattice Surgery
- Quantum Error Correction: An Introductory Guide
- Low-distance Surface Codes under Realistic Quantum Noise
- Fast Decoders for Topological Quantum Codes
- Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
- A Neural Decoder for Topological Codes
- Machine-learning-assisted correction of correlated qubit errors in a topological code
- Decoding Small Surface Codes with Feedforward Neural Networks
- Deep Neural Network Probabilistic Decoder for Stabilizer Codes
- An efficient Markov chain Monte Carlo algorithm for the surface code
- Comparing neural network based decoders for the surface code
- Cellular-automaton decoders for topological quantum memories
- Topological code Autotune
- Optimal complexity correction of correlated errors in the surface code
- Neural Network Decoders for Large-Distance 2D Toric Codes
- General framework for constructing fast and near-optimal machine-learning-based decoder of the topological stabilizer codes
- Adaptive weight estimator for quantum error correction
- Neural ensemble decoding for topological quantum error-correcting codes
- Analytic asymptotic performance of topological codes
- A decoding algorithm for CSS codes using the X/Z correlations
- Threshold error rates for the toric and surface codes