[MUSIC] So I showed you some examples of
neural networks in computer vision and doing classification. Is there a labrador
retriever in this image? But they can do quite a bit more. So, for example, we can do image parsing. So in this example, for
every picture in the image, you're trying to classify it and
discover regions. So in the center top image,
you see a region of sky, another region of grass, and so on. And this kind of image description,
or is called scene understanding, is pretty cool, and you know networks
again, provided significant gains. But if we go back to
the beginning of the module when we discussed a new way to shop for
shoes or dresses, the thing that we're really trying to
do there is retrieve similar images. So, for example, if I give you
the input of this boring black shoe, what neural network with output. Deep neural network is
the shoes that are shown here. A bunch of boring black shoes. Now, if I do this a little
bit more stylish boot, you'll see that it gives you a variety
of interesting boots like that. Similarly, for heels, for
brown shoes, for sneakers and so on. So this is the core of the concept that
we're using in the demo that we showed at the beginning of the module. [MUSIC]