An algorithm to compute the softmax layer in neural networks using low floating-point precision arithmetic.
See the pdf file for the algorithm.
-
Notifications
You must be signed in to change notification settings - Fork 0
DanielEftekhari/numerically-efficient-softmax-algorithm
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
An algorithm to compute the softmax layer in neural networks using low floating-point precision arithmetic.