Population Based Training of Neural Networks

arXiv: Learning, Volume abs/1711.09846, 2017.

Cited by: 262|Bibtex|Views305
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In this work we present emph{Population Based Training (PBT)}, a simple asynchronous optimisation algori...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments