Most generally, a machine learning algorithm can be through of as a black box. It takes inputs and gives outputs.

For example, we may create a model that predicts the weather tomorrow, based on meteorological data about the past few days.

The “black box” in fact is a mathematical model. The machine learning algorithm will follow a kind of trial-and-error method to determine the model that estimates the outputs, given inputs.

Once we have a model, we must train it. Training is the process through which, the model learns how to make sense of input data.