dogear

enter for all results · esc to close

Self-Normalizing Neural Networks

arxiv.orgsite

Appearance of the incredible SELU activation function.

from
Education
added
2026-10-10
likes
0

similar

  1. Fast and Accurate Deep Network Learning by Exponential Linear Units arxiv.org

    ELU activation function for CIFAR vision tasks.

    site link ↗
  2. Globally Normalized Transition-Based Neural Networks arxiv.org

    This paper describes the models behind SyntaxNet.

  3. The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) jalammar.github.io

    Understand the different approaches used for NLP's ImageNet moment.

  4. 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.”