Advantages of versatile neural-network decoding for topological codes

TL;DR

This paper explores the use of versatile feedforward neural networks as decoders for topological stabilizer codes, demonstrating improved error correction thresholds and adaptability to complex noise models without prior noise knowledge.

Contribution

It introduces a neural network-based decoding approach for topological codes, showing its effectiveness and flexibility over traditional decoders.

Findings

Neural decoders outperform traditional decoders in error-correction thresholds.

Neural decoders adapt well to various noise models, including correlated errors.

Designing decoders with neural networks is simplified and does not need prior noise information.

Abstract

Finding optimal correction of errors in generic stabilizer codes is a computationally hard problem, even for simple noise models. While this task can be simplified for codes with some structure, such as topological stabilizer codes, developing good and efficient decoders still remains a challenge. In our work, we systematically study a very versatile class of decoders based on feedforward neural networks. To demonstrate adaptability, we apply neural decoders to the triangular color and toric codes under various noise models with realistic features, such as spatially-correlated errors. We report that neural decoders provide significant improvement over leading efficient decoders in terms of the error-correction threshold. Using neural networks simplifies the process of designing well-performing decoders, and does not require prior knowledge of the underlying noise model.