Neural networks are made up of nodes (each representing a Logistic regression) with layers. They are trained to map an input vector X to an output vector Y based on the training data. The hidden layers of a network contain neurons, connections, and activation functions that occur between the input and output. An activation function is applied at each layer to correctly connect the input and output. Different types of networks may use diverse types of activation functions to correctly identify the nature of how the input and output are related. In the figure out of the 4 neurons, the Logistic regression representation of two of them are shown.