In the last video we saw LSTMs and
how they work with cell state to help keep context in a way that
helps with understanding language. Well, words that aren't immediate
neighbors can affect each other's context. In this video, you'll see some other
options of RNN including convolutions, Gated Recurrent Units also called GRUs,
and more on how you can write the code for
them. You'll investigate the impact
that they have on training. I'm not going to go into
depth on how they work, and that information is available in the
deep learning specialization from Andrew. So do check it out there.