GitHub / DanielEftekhari / numerically-efficient-softmax-algorithm
An algorithm to compute the softmax layer in neural networks using low floating-point precision arithmetic.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DanielEftekhari%2Fnumerically-efficient-softmax-algorithm
PURL: pkg:github/DanielEftekhari/numerically-efficient-softmax-algorithm
Stars: 0
Forks: 0
Open issues: 0
License: None
Language:
Size: 361 KB
Dependencies parsed at: Pending
Created at: almost 2 years ago
Updated at: almost 2 years ago
Pushed at: almost 2 years ago
Last synced at: almost 2 years ago
Topics: deep-learning, floating-point-arithmetic, softmax, softmax-layer