A Recurrent Neural Network (RNN) is a class of artificial neural network that has memory or feedback loops that allow it to better recognize patterns in data.

Which network has feedback loop?

A recurrent network combines the feedback and the feedforward connections of neural networks (see Figure 2.8). In other words, it is simply a neural network with loops connecting the output responses to the input layer. Thus, the output responses of the network function as additional input variables.

In which type of artificial neural network feedback loops are allowed?

RNNs differ in that they retain information about the input previously received. They are networks with feedback loops that allow information to persist -- a trait that is analogous to short-term memory.