Last week, we looked at recurrent neural
networks including a simple RNN and an LSTM. You saw how they could be useful in
learning a sequence like the one that we've been looking at. And how the LSTMs removed some of
the issues we had with an RNN. This week, you'll go one step further, combining convolutions with LSTMs
to get a very nicely fitting model. We'll then apply that to real
world data instead of this synthetic data set that we've been working
on since the beginning of this course. Here's the LSTM that you
looked at last week, except that I've added something at
the beginning of the sequential stack. It's a convo D where we'll
try to learn 32 filters. It's a one dimensional convolution. So we'll take a five number window and
multiply out the values in that window by the filter values, in much the
same way as image convolutions are done. Check back to the convolutions
course to learn more about that.