AI Blog

AI Blog

by Michele Laurelli

ReLU (Rectified Linear Unit)

/ˈriːluː/
Concept
Definition

An activation function that outputs the input if positive, otherwise zero: f(x) = max(0, x).

ReLU is the most popular activation function in deep learning due to its simplicity and effectiveness. It helps mitigate vanishing gradient problems and enables faster training compared to sigmoid or tanh.

Examples

1

Hidden layers in CNNs

2

Deep neural networks

3

Most modern architectures

Michele Laurelli - AI Research & Engineering