Deep Q-learning decoder for depolarizing noise on the toric code
David Fitzek, Mattias Eliasson, Anton Frisk Kockum, Mats Granath
Abstract
This paper presents an artificial intelligence-based decoder for quantum error correction of the toric code. A neural network is trained, using reinforcement learning, to suggest error-correcting operations on the physical qubits to best avoid logical errors. By learning to take advantage of the correlations between bit-flip and phase-flip errors, it can outperform the standard matching decoder for depolarizing noise.
Topics & Concepts
Computer scienceAlgorithmCode (set theory)Artificial neural networkNoise (video)Error detection and correctionMatching (statistics)Toric codeDecoding methodsBipartite graphQuantumHamming codeReinforcement learningComparatorTheoretical computer scienceArtificial intelligenceDepolarizationElectronic engineeringDeep learningEncoding (memory)DetectorFilter (signal processing)BackpropagationQubitQuantum Computing Algorithms and ArchitectureQuantum Information and CryptographyError Correcting Code Techniques