Types of RNN Architectures

In this lesson, we are going to discuss different variations of Recurrent Neural Networks and their applications. So let’s get started.

Types of RNN architectures

There are five types of RNN architectures:

One to one (non-sequential)

This is the most simple one. It basically represents a Multi-Layer Perceptron because it takes a single input and generates a single output. The architecture is depicted below.