Math & Optimization · beginner · concept 36 of 176
Activation Functions
Non-linear functions applied to neuron outputs, they give neural networks the ability to learn complex patterns. ReLU, Sigmoid, Tanh, GELU, and Swish are the most common.
Key terms
ReLUSigmoidTanhGELUVanishing gradient
Learn these first
Videos
▶ Neural Networks Pt. 3: ReLU In Action!!! ↗
StatQuest with Josh Starmer · YouTube
▶ Activation Functions (C1W3L06) ↗
DeepLearningAI · YouTube
Guides and articles
CS231n Deep Learning for Computer Vision ↗
Stanford CS231n
5.1. Multilayer Perceptrons — Dive into Deep Learning 1.0.3 documentation ↗
Dive into Deep Learning
Courses, papers, and more
This unlocks