AI Blog

AI Blog

by Michele Laurelli

Sigmoid Function

/ˈsɪɡmɔɪd/
Concept
Definition

An activation function that maps inputs to values between 0 and 1: f(x) = 1/(1 + e^(-x)).

Sigmoid is used for binary classification output layers and was historically popular for hidden layers. However, it suffers from vanishing gradient problems in deep networks.

Examples

1

Binary classification output

2

Logistic regression

3

Gate mechanisms in LSTM

Michele Laurelli - AI Research & Engineering