After processing the input, the hidden layer sends its result to the output layer. As the name suggests, the output layer emits the output. The number of neurons in the output layer relates to the type of problem we want our network to solve. If it is a binary classification, then the number of neurons in the output layer tells us which class the input belongs to. If it is a multi-class classification say, with five classes, and if we want to get the probability of each class being an output, then the number of neurons in the output layer is five, each emitting the probability. If it is a regression problem, then we have one neuron in the output layer.