Activation Layer
/ˌæktɪˈveɪʃən ˈleɪər/
A layer that applies a non-linear activation function element-wise to its input.
In italiano: Layer di AttivazioneActivation layers introduce non-linearity, enabling networks to learn complex patterns. Often placed after linear transformations (convolution, dense layers). Common: ReLU, sigmoid, tanh layers.
Examples
- ReLU activation layer
- Sigmoid output layer
- Tanh hidden layer