Recurrent Neural Networks, Explained and Visualized from the Ground Up

<p>Recurrent Neural Networks (RNNs) are neural networks that can operate sequentially. Although they&rsquo;re not as popular as they were even just several years ago, they represent an important development in the progression of deep learning and are a natural extension of feedforward networks.</p> <p>In this post, we&rsquo;ll cover the following:</p> <ul> <li>The step from feedforward to recurrent networks</li> <li>Multilayer recurrent networks</li> <li>Long short-term memory networks (LSTMs)</li> <li>Sequential output (&lsquo;text output&rsquo;)</li> <li>Bidirectionality</li> <li>Autoregressive generation</li> <li>An application to machine translation (a high-level understanding of Google Translate&rsquo;s 2016 model architecture)</li> </ul> <p>The aim of the post is not only to explain how RNNs work (there are plenty of posts which do that), but to explore their design choices and high-level intuitive logic with the aid of illustrations. I hope this article will provide some unique value not only to your grasp of this particular technical topic but also more generally the flexibility of deep learning design.</p> <p><a href="https://towardsdatascience.com/recurrent-neural-networks-explained-and-visualized-from-the-ground-up-51c023f2b6fe">Website</a></p>