Overaching view on RNNs

doc/src/Recurrent/Recurrent.do.txt

@@ -5,3 +5,22 @@ DATE: today
 
 !split
 ===== Recurrent neural networks: Overarching view =====
+
+We have mostly looked at feedforward neural networks, where the
+activations flow only in one direction, from the input layer to the
+output layer.
+
+A recurrent neural network (RNN) looks very much like a feedforward
+neural network, except it also has connections pointing
+backward. Let’s look at the simplest possible RNN, composed of just
+one neuron receiving inputs, producing an output, and sending that
+output back to itself.
+
+RNNs are used to analyze time series data such as stock prices, and
+tell you when to buy or sell. In autonomous driving systems, they can
+anticipate car trajectories and help avoid accidents. More generally,
+they can work on sequences of arbitrary lengths, rather than on
+fixed-sized inputs like all the nets we have discussed so far. For
+example, they can take sentences, documents, or audio samples as
+input, making them extremely useful for natural language processing
+systems such as automatic translation and speech-to-text.