Usually, recurrent networks are networks that are capable of influencing themselves by way of recurrences, e.g. by including the network output down this page computation steps. There are lots of types of recurrent networks of nearly arbitrary form, and the majority of them are known as recurrent neural networks.Recurrent multilayer perceptrons this kind of a recurrent network is capable to compute more than the ordinary MLP: If the recurrent weights are set to 0, the recurrent network is going to be reduced to an ordinary MLP.