# Overview of Recurrent Neural Networks

Principally, there are 4 ways to construct an RNN architecture (the 4 right ones in the picture):

### 1. One-to-one

You might use a Dense layer as you are not processing sequences:

model.add(Dense(output_size, input_shape=input_shape))


### 2. One-to-many

This option is not supported well as chaining models is not very easy in Keras so the following version is the easiest one:

model.add(RepeatVector(number_of_times, input_shape=input_shape))


### 3. Many-to-one

Actually your code snippet is (allmost) example of this approach:

model = Sequential()


### 4. Many-to-many

This is the easiest snippet when length of input and output matches the number of recurent steps:

model = Sequential()