© Nikhil Ketkar 2017

Nikhil Ketkar, Deep Learning with Python, https://doi.org/10.1007/978-1-4842-2766-4_6

6. Recurrent Neural Networks

Nikhil Ketkar

(1)Bangalore, Karnataka, India

Recurrent Neural Networks (RNNs) in essence are neural networks that employ recurrence, which is basically using information from a previous forward pass over the neural network. Essentially, all RNN’s can be described as a recurrence relationship. RNNs are suited and have been incredibly successful when applied to problems wherein the input data on which the predictions are to be made is in the form of a sequence (series of entities where order is important).

RNN Basics

Let us start by describing the moving parts of a RNN. First, we introduce some notation .

  1. We will ...

Get Deep Learning with Python: A Hands-on Introduction now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.