Congratulations on coming to the end of this second course. Just cause you've learned how
to build bigger confidence, how to implement
data augmentation, how to implement
transfer learning as well also how to use multi-class cross size but there's still a lot
more to learn. Lot's the examples you've seen so far have used
many computer vision. In the next course, you'll
learn how to deal with natural language processing
to how to work with texts. It's going to be a lot
of fun switching gears as well from dealing with pixels to dealing with characters
and dealing with words. We'll take a look at
how to tokenize words, how to generate embeddings, so that we can learn
off of embeddings. An embedding is where we can turn a word into basically a vector in a multi-dimensional space and from the direction that vector points in we can
start ascertaining the semantics of that word. We'll be going into
all of that and how words also work in sequence and different sequence
models for learning what the context of
a sentences and what the semantics of
the sentence is, yeah. That sounds exciting. So I think natural language
processing is really taking off partly because
of deep learning. So in the next course, you'll learn a lot about that and give that built some of
these exciting models yourself. So let's go to the next course.