AI glossary · Machine learning
Activation function
An activation function decides how strongly each unit in a neural network passes its signal on, which lets the network learn complex, non-linear patterns.
Also called ReLU, sigmoid
In more detail
Without activation functions, stacking layers would be no more powerful than a single layer. Common ones include ReLU, which passes positive values and blocks negatives, and sigmoid, which squeezes values between 0 and 1.
They are a small but essential part of every neural network.
Related terms
Neural networkA neural network is an AI model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.Deep learningDeep learning is a type of machine learning that uses neural networks with many layers to learn complex patterns in text, images and sound.BackpropagationBackpropagation is how a neural network learns from mistakes: it works backwards from the error to find how much each connection caused it, then adjusts them.
Browse related tools
AI tools listed on BroUseAI in these categories.
