Explaining RNNs without neural networks

Vanilla recurrent neural networks (RNNs) form the basis of more sophisticated models, such as LSTMs and GRUs. There are lots of great articles, books, and videos that describe the functionality, mathematics, and behavior of RNNs so, don't worry, this isn't yet another rehash. (See below for a list of resources.) My goal is to present an explanation that avoids the neural network metaphor, stripping it down to its essence—a series of vector transformations that result in embeddings for variable-length input vectors.

It is so easy to get bogged down in the mathematics of RNNs that new learners lose perspective of the dynamics. I love that you have flipped that around.

I favor the approach of understanding the dynamics of machine learning. The mathematics are then easily distilled from the nature of the process.

This is a very clear description of that process. Thank you for it!

This is really great. I'm so glad that someone took the time to explain what is really going on. Thanks...hopefully you'll do more!

Great article, thanks.

hella explanation! Even I can understand