1703.02642
CMU DeepLens: Deep learning for automatic image-based galaxy-galaxy strong lens finding
Lanusse, et al
Train and validate the model on a set of 20k LSST-like mock observations including a range of lensed systems of various sizes and S/N. Find on the simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1.4" and S/N larger than 20 on individual g-band LSST exposures. Finally, emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. Code publicly available at GitHub.com/McWilliamsCenter/CMUDeepLens.
No comments:
Post a Comment