AI glossary
What is activation function?
Short answer
A function applied to a neuron's weighted sum (e.g. ReLU, sigmoid) that adds non-linearity, letting stacked layers learn complex patterns.
For example
ReLU simply turns negative numbers into zero and keeps positive ones. That small bend is what lets a stack of layers draw curved boundaries instead of only straight lines.
Learn it in a free lesson
Questions
What is activation function in simple terms?
A function applied to a neuron's weighted sum (e.g. ReLU, sigmoid) that adds non-linearity, letting stacked layers learn complex patterns.
What is an example of activation function?
ReLU simply turns negative numbers into zero and keeps positive ones. That small bend is what lets a stack of layers draw curved boundaries instead of only straight lines.
Where can I learn about activation function for free?
AI in Bed explains it in the free lesson "Neural networks, gently" (Beginner level, 6 minutes), with no sign-up.