What is a model in the mathematical sense

When we talk about a model in machine learning, it helps to forget about all the hype around “artificial intelligence” and complex abstractions. In the mathematical sense, a model is just a function: it takes some input data and returns a result. The key difference is that this function is not fixed once and for all — it has parameters that we can tune.

• Function as the basis of the model
• Error as a measure of quality
• Learning as minimizing error