Machine learning uncovers new cosmological information
arXiv:1810.12220 · doi:10.1038/s41550-018-0623-9
Abstract
Large cosmological datasets have been probing the properties of our universe and constraining the parameters of dark matter and dark energy with increasing precision. Deep learning techniques have shown potential to be smarter, and to greatly outperform human-designed statistics.
A lightly edited version of this submission appeared as an invited News & Views article in the October 29 issue of Nature Astronomy