Click the square on the bottom right of the video to view full-screen.
More information about this lesson available at the lesson wiki.
For the start of today’s lesson we’ll cover the CycleGAN, which is a breakthrough idea in GANs that allows us to generate images even where we don’t have direct (paired) training data. We’ll use it to turn horses into zebras, and visa versa; this may not be an application you need right now… but the basic idea is likely to be transferable to a wide range of very valuable applications. One of our students is already using it to create a new form of visual art.
But generative models (and many other techniques we’ve discussed) can cause harm just as easily as they can benefit society. So we spend some time today talking about data ethics. It’s a topic that really deserves its own whole course; whilst we can’t go into the detail we’d like in the time available, hopefully you’ll get a taste of some of the key issues, and ideas for where to learn more.
We finish today’s lesson by looking at style transfer, an interesting approach that allows us to change the style of images in whatever way we like. The approach requires us to optimize pixels, instead of weights, which is an interesting different way of looking at optimization.