Critical Hyper-Parameters: No Random, No Cry

Published: Jun 10, 2017
Abstract
The selection of hyper-parameters is critical in Deep Learning. Because of the long training time of complex models and the availability of compute resources in the cloud, null optimization schemes - where the sets of hyper-parameters are selected in advance (e.g. on a grid or in a random manner) and the training is executed in parallel - are commonly used. It is known that grid search is sub-optimal, especially when only a few critical...
Paper Fields
Paper Details
Title
Critical Hyper-Parameters: No Random, No Cry
Published Date
Jun 10, 2017
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.