Deep learning is a machine learning research area that is based on a particular type of learning mechanism. It is characterized by the effort to create a learning model at several levels, in which the most profound levels take as input the outputs of previous levels, transforming them and always abstracting more. This insight on the levels of learning is inspired by the way the brain processes information and learns, responding to external stimuli.

Each learning level corresponds, hypothetically, to one of the different areas which make up the cerebral cortex.