AI GlossaryActivation Function

[Neural Networks]

Activation Function.

A mathematical function that determines the output of a neuron based on its weighted input sum.

In-depth explanation

01

Activation functions introduce non-linearity, enabling neural networks to learn complex patterns. Without them, a network would just be a linear transformation. Common functions include ReLU (max(0, x)), sigmoid (1/(1+e^-x)), tanh, and softmax (for multi-class output). Choice of activation function affects training dynamics and model capabilities.

Examples

02
EX. 01

ReLU in hidden layers

EX. 02

Softmax in classification output

[NEXT] — APPLY THE CONCEPT

Master Activation Function.

Learn how to apply this concept with hands-on projects in our comprehensive AI programs.