Long Short-Term Memory (LSTM), models are a special case of RNNs, Recurrent Neural Networks. A full, rigorous description of them is out of the scope of this book; in this section, we will just provide the essence of them.
Simply speaking, RNN works on sequences: they accept multidimensional signals as input, and they produce a multidimensional output signal. In the following figure, there's an example of an RNN able to cope with a timeseries ...