Summary
The foundational concepts of sequential models were explained in this chapter, which aimed to give you a basic understanding of the techniques and methodologies of such techniques. In this chapter, we presented RNNs, which are great for handling sequential data. A GRU is a type of RNN that was introduced by Cho et al. in 2014 as a simpler alternative to LSTM networks.
Like LSTMs, GRUs are designed to learn long-term dependencies in sequential data, but they do so using a different approach. GRUs use a single gating mechanism to control the flow of information into and out of the hidden state, rather than the three gates used by LSTMs. This makes them easier to train and requires fewer parameters, making them more efficient to use.
The next chapter introduces some advanced techniques related to sequential models.
Learn more on Discord
To join the Discord community for this book – where you can share feedback, ask questions to the author, and learn about...
