In this type, number of inputs and outputs are not the same.

Example: Machine Translation

University of Michigan - Ann Arbor

Google

If we consider Tx the length of input and Ty the length of output:

1- Many-to-many ( Tx=Ty)

2- Many-to_many (Tx!=Ty)

3- Many-to-one

4-One_to_Many


Different types of RNN (in terms of input/output)

Machine Learning Yearning, a free ebook from Andrew Ng, teaches you how to structure Machine Learning projects.
https://www.deeplearning.ai/machine-learning-yearning/

Note: The content of the book is aligned with the Coursera Deeplearning.ai specialization.  https://www.deeplearning.ai/deep-learning-specialization/ 

Machine Learning Yearning (Deeplearning.ai)

In this type, there are many input and also there are many output in the model.

Example: Name entity Recognition.

Many_to_Many RNN (Tx=Ty)

Many_to_Many (Tx != Ty)

In this type, there is one input to the model with many outputs.

Example: Music generation

One_to_Many

In this type, there are many inputs to the model, but only one output.


Example: sentiment analysis

Learn Before

Related