← World of AI
Neural Networks
Activation Functions
Functions that introduce non-linearity into neural-network computations.
An activation function determines how a neuron responds after its weighted inputs and bias are combined. Without non-linear activation functions, a deep network would behave like a single linear transformation.
Common choices include ReLU, sigmoid, tanh, GELU and softmax. Different functions affect gradient flow, training stability and the type of output produced by the network.
Also in Neural Networks
JOIN NOW
Begin the first module
It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.
Join any time · Build AI skills at your pace