The return of neural networks (1986-present) In the middle of the years80, four groups of researchers independently discovered the“back-propagation" learning mechanism that allowed the development ofnetworks of neurons capable of learning very complex functions- plexes (oddly enough, this rule had already been proposed in 1969, buthad had no echo in the scientific community). Since then, the AP- machine learning has become one of the most active areas ofAI, and has been successfully applied to many practical problems (such as, for example, data mining).