AI glossary
What is machine learning?
Machine learning is the branch of AI where a system learns patterns from examples instead of following rules someone programmed by hand.
In traditional programming a person writes the rules: if the email contains this word, it is spam. In machine learning you show the system thousands of emails already labeled spam or not spam, and the algorithm adjusts its own parameters until it gets as many right as it can.
That adjustment is training, and what comes out of it is a model. Using the model afterwards on new data is called inference.
There are different ways to learn: supervised (with labeled examples), unsupervised (finding structure in unlabeled data) and reinforcement learning (trying things and getting rewards or penalties). Deep learning is machine learning with many-layered neural networks.
An example
A model that estimates an apartment's price from thousands of past sales (size, neighborhood, age) is supervised machine learning.