Efficient softmax approximation for GPUs on ShortScience.org

proceedings.mlr.press
scholar.google.com

Efficient softmax approximation for GPUs
Grave, Edouard and Joulin, Armand and Cissé, Moustapha and Grangier, David and Jégou, Hervé
International Conference on Machine Learning - 2017 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Marek Rei 6 years ago

Modification of the 2-level hierarchical softmax for better efficiency. An equation of computational complexity is used to find the optimal number of words in each class. In addition, the most common words are considered on the same level as other classes.

https://i.imgur.com/dbKS3gh.png

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private