Fully convolutional 3D neural network decoders for surface codes with syndrome circuit noise

TL;DR

This paper demonstrates that convolutional neural networks can effectively decode surface codes under circuit noise, achieving competitive thresholds and improved latency for large code distances.

Contribution

It introduces a scalable, vectorised ANN decoding scheme exploiting spatiotemporal syndrome data, outperforming traditional methods in latency and maintaining high thresholds.

Findings

Achieved depolarisation thresholds up to 0.7% for large surface codes.

Generalised decoding performance up to code distance 97.

Improved latency over MWPM starting at code distances 33 and 89.

Abstract

Artificial Neural Networks (ANNs) are a promising approach to the decoding problem of Quantum Error Correction (QEC), but have observed consistent difficulty when generalising performance to larger QEC codes. Recent scalability-focused approaches have split the decoding workload by using local ANNs to perform initial syndrome processing and leaving final processing to a global residual decoder. We investigated ANN surface code decoding under a scheme exploiting the spatiotemporal structure of syndrome data. In particular, we present a vectorised method for surface code data simulation and benchmark decoding performance when such data defines a multi-label classification problem and generative modelling problem for rotated surface codes with circuit noise after each gate and idle timestep. Performance was found to generalise to rotated surface codes of sizes up to $d=97$, with depolarisation parameter thresholds of up to $0.7\%$ achieved, competitive with h Minimum Weight Perfect Matching (MWPM). Improved latencies, compared with MWPM alone, were found starting at code distances of $d=33$ and $d=89$ under noise models above and below threshold respectively. These results suggest promising prospects for ANN-based frameworks for surface code decoding with performance sufficient to support the demands expected from fault-tolerant resource estimates.