Recurrent neural networks (RNNs) are a class of neural networks that are naturally suited to processing time-series data and other sequential data. Here we briefly introduce typical neural networks in addition to RNN's as an extension to feedforward networks. In the end, we're going to inspect some of the most popular recurrent architectures in use, including long short-term memory (LSTM). Prerequisite: Familiarity with basic machine learning and optimization concepts.