• Rabuñal Dopico, Juan Ramón
• Pereira Loureiro, Javier
• Miguélez Rico, Mónica

In this chapter, we state an evolution of the Recurrent ANN (RANN) to enforce the persistence of activations withim the meurons to create activation context that generate correct outputs through time, In this new focus we want to file more information in the neurón´s connections. To do this, the connection´s representation goes from the unique values up to a finction that generates the neuron´s output. The training process to this type of ANN has to calculate the gradient that identifies the function. To train this RANN we developed a GA based system that finds the best gradient set to solve each problem.