RNN can be architected in multiple ways. Some of the possible ways are as follows:
The box in the bottom is the input, followed by the hidden layer (as the middle box), and the box on top is the output layer. The one-to-one architecture is the typical neural network with a hidden layer between the input and the output layer. The examples of different architectures are as follows:
| Architecture | Example |
| One-to-many | Input is image and output is caption of image |
| Many-to-one | Input is a movie's review (multiple words in input) and output is sentiment associated with the review |
| Many-to-many | Machine translation of a sentence in one language to a sentence in another language |
