Login / Signup

Competition-level code generation with AlphaCode.

Yujia LiDavid ChoiJunyoung ChungNate KushmanJulian SchrittwieserRémi LeblondTom EcclesJames KeelingFelix GimenoAgustin Dal LagoThomas HubertPeter ChoyCyprien de Masson d'AutumeIgor BabuschkinXinyun ChenPo-Sen HuangJohannes WelblSven GowalAlexey CherepanovJames MolloyDaniel J MankowitzEsme Sutherland RobsonPushmeet KohliNando de FreitasKoray KavukcuogluOriol Vinyals
Published in: Science (New York, N.Y.) (2022)
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist programmers or even generate programs themselves could make programming more productive and accessible. Recent transformer-based neural network models show impressive code generation abilities yet still perform poorly on more complex tasks requiring problem-solving skills, such as competitive programming problems. Here, we introduce AlphaCode, a system for code generation that achieved an average ranking in the top 54.3% in simulated evaluations on recent programming competitions on the Codeforces platform. AlphaCode solves problems by generating millions of diverse programs using specially trained transformer-based networks and then filtering and clustering those programs to a maximum of just 10 submissions. This result marks the first time an artificial intelligence system has performed competitively in programming competitions.
Keyphrases
  • artificial intelligence
  • neural network
  • public health
  • mental health
  • machine learning
  • big data
  • deep learning
  • working memory
  • single cell
  • body composition
  • resistance training