Applications of RNNs

So far, we have only talked about one-to-one-mapped RNNs, where the current output depends on the current input as well as the previously observed history of inputs. This means that there’s an output for the sequence of previously observed inputs and the current input. However, in the real world, there can be situations where there is only one output for a sequence of inputs, a sequence of outputs for a single input, and a sequence of outputs for a sequence of inputs where the sequence sizes are different. In this lesson, we’ll look at the four settings of RNN models and the applications they would be used in.

• One-to-one RNNs

• One-to-many RNNs

• Many-to-one RNNs

• Many-to-many RNNs

One-to-one RNNs

In one-to-one RNNs, the current input depends on the previously observed inputs. Such RNNs are appropriate for problems where each input has an output, but the output depends both on the current input and the history of inputs that led to the current input. An example of such a task is stock market prediction, where we output a value for the current input, and this output also depends on how the previous inputs have behaved. Another example would be scene classification, where each pixel in an image is labeled (for example, labels such as car, road, and person). Sometimes $x_{t+1}$ can be the same as $y_t$ for some problems. For example, in text generation problems, the previously predicted word becomes an input to predict the next word. The following figure depicts a one-to-one RNN: