Recurrent Neural Network (RNN) is an artificial neural network suitable for processing sequence data. It was proposed by Michael I. Jordan in 1986 and simplified by Jeffrey L. Elman in 1990 to form the current RNN model containing a single self-connected node. RNN can transmit information cyclically in the network through its unique internal ring connection, realizing the storage and processing of sequence information.

The working principle of RNN is to store the information of the previous time step through the state of the hidden layer, so that the output of the network depends on the current input and the previous state. This design allows RNN to take into account the time series characteristics of data when processing sequential data such as text, voice and video.