What is the role of the activation function in a neural network?

The activation function in a neural network introduces non-linearity into the model, enabling it to learn complex patterns in the data. Without activation functions, a neural network would essentially behave like a linear regression model, as layers of linear transformations would still yield a linear output. Common activation functions, such as ReLU, sigmoid, and tanh, allow the network to approximate various functions and make decisions based on the learned features. By doing so, they enhance the model's ability to capture intricate relationships within the data.