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.
arXiv commentA lightly edited version of this submission appeared as an invited News & Views article in the October 29 issue of Nature Astronomy
References in corpus (8)
- KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing
- Cosmology with cosmic shear observations: a review
- Cosmology Constraints from the Weak Lensing Peak Counts and the Power Spectrum in CFHTLenS
- Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
- KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics - II: Inference from Shear Peaks using N-body Simulations
- Non-Gaussian information from weak lensing data via deep learning
- 3D Cosmic Shear: Cosmology from CFHTLenS
- The cosmological information of shear peaks: beyond the abundance