An extension of SWA can obtain efficient Bayesian model averaging, as well as high quality uncertainty estimates and calibration in deep learning.SWA is shown to improve the stability of training as well as the final average rewards of policy-gradient methods in deep reinforcement learning.SWA provides state-of-the-art performance on key benchmarks in semi-supervised learning and domain adaptation.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |