no code implementations • 26 Sep 2019 • Md Sazzad Hossain, Andrew P Paplinski, John M Betts
Our DFL method is an improvement on the recently reported Focal Loss (FL) cross-entropy function, which proposes a scaling method that puts more weight on the examples that are difficult to classify over those that are easy.
no code implementations • 5 Apr 2018 • Yanan Li, Haixiang Guo, Andrew P Paplinski
In this paper, we use the semi-supervised learning to solve the problem of ever-increasing amount of unlabelled data available for interpretation.