An RNN is a type of artificial neural network made up of "cells" that maintain an internal state (or memory). They are designed to process sequential data where different sequences can have different lengths. RNNs process sequence elements one at a time, updating their cells' internal states as they do so -- thus elements early in the sequence can have an influence in a cell's output later in the sequence. The most popular RNNs are the LSTM (long short-term memory) and GRU (gated recurrent unit) networks -- they differ in how the internal state of each cell is updated. RNNs can be used in applications such as sentiment analysis, translation, and music generation.