• Rivero Cebrián, Daniel
• Varela Pérez, Miguel
• Pereira Loureiro, Javier

A technique is described in this chapter that makes it possible to extract the knowledge held by previously trained artificial neural networks. This makes it possible for them to be used in a number of areas (such as medicine) where it is necessary to know they work, as well as having a network that functions. This chapter explains how to carry out this process to extract knowledge, defined as rules. Special emphasis is placed on extracting knowledge from recurrent neural network in particular when applied in predicting time series.