Decoding small surface codes with feedforward neural networks

Savvas Varsamopoulos*, Ben Criger, Koen Bertels

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

59 Citations (Scopus)


Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

Original languageEnglish
Article number015004
Pages (from-to)1-12
Number of pages12
JournalQuantum Science and Technology
Issue number1
Publication statusPublished - 1 Jan 2018


  • artificial neural networks
  • fault tolerance
  • quantum error correction
  • surface codes


Dive into the research topics of 'Decoding small surface codes with feedforward neural networks'. Together they form a unique fingerprint.

Cite this