Self-Normalizing Neural Networks
Appearance of the incredible SELU activation function.
- from
- Education
- added
- 2026-10-10
- likes
- 0
similar
-
Fast and Accurate Deep Network Learning by Exponential Linear Units arxiv.org
ELU activation function for CIFAR vision tasks.
-
Globally Normalized Transition-Based Neural Networks arxiv.org
This paper describes the models behind SyntaxNet.
-
ICML'20, 2020. [All Versions].
-
The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) jalammar.github.io
Understand the different approaches used for NLP's ImageNet moment.
-
The Annotated Transformer nlp.seas.harvard.edu
Good for understanding the "Attention Is All You Need" (AIAYN) paper.
-
Education › Other Math Theory > Gradient Descent Algorithms & Optimization Theory: “Appearance of the incredible SELU activation function.”