Recurrent neural networks (RNNs) have in general no probabilistic component in a model. With a given fixed input and target from data, the RNNs learn the intermediate association between various layers. The inputs, outputs, and internal representation (hidden states) are all real-valued vectors.
In a traditional NN, it is assumed that every input is independent of each other. But with sequential data, the input at a given stage \( t \) depends on the input from the previous stage \( t-1 \)