Menu

Activation Functions

Activation Functions

Activation functions help the neural network learn complex patterns by introducing non-linearity.

This project uses two activation functions.

ReLU

ReLU (Rectified Linear Unit) is commonly used in hidden layers. It allows the model to learn efficiently and speeds up training.

Softmax

Softmax is used in the output layer for multi-class classification. It converts the output values into probabilities, making it easier to predict the correct image class.