Deep Learning with PyTorch

Recursive neural networks

RNNs are among the most powerful models that enable us to take on applications such as classification, labeling on sequential data, generating sequences of text (such as with the SwiftKey Keyboard app which predicts the next word), and converting one sequence to another such as translating a language, say, from French to English. Most of the model architectures such as feedforward neural networks do not take advantage of the sequential nature of data. For example, we need the data to present the features of each example in a vector, say all the tokens that represent a sentence, paragraph, or documents. Feedforward networks are designed just to look at all the features once and map them to output. Let's look at a ...