Machine learning for quantum physics

See allHide authors and affiliations

Science  10 Feb 2017:
Vol. 355, Issue 6325, pp. 580
DOI: 10.1126/science.aam6564

You are currently viewing the summary.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution


Machine learning has been used to beat a human competitor in a game of Go (1), a game that has long been viewed as the most challenging of board games for artificial intelligence. Research is now under way to investigate whether machine learning can be used to solve long outstanding problems in quantum science. On page 602 of this issue, Carleo and Troyer (2) use machine learning on one of quantum science's greatest challenges: the simulation of quantum many-body systems. Carleo and Troyer used an artificial neural network to represent the wave function of a quantum many-body system and to make the neural network "learn" what the ground state (or dynamics) of the system is. Their approach is found to perform better than the current state-of-the-art numerical simulation methods.