Python implementation of an artificial neural network, which consists of a set of perceptrons.

Perceptrons are used for classification of a single input into one of several possible non-binary outputs. These serve as linear classifiers, which make predictions on the output based on a linear prediction function by combining a set of weights with the feature vector.

Therefore, we can use a combination of perceptrons to construct a neural network and train the network on a set of data, in order to make a prediction on a set of examples.