One branch of deep learning deals with generative models, i.e. how to generate new data that is similar to the properties of the training data. One such example is the simulation of possible future (e.g. what will the the next frame in a video), or how to create new faces from celeb images (https://www.youtube.com/watch?v=XOxxPcy5Gr4). The task of the student is to learn about Generative Adversarial Networks (GAN) and conduct an individually chosen machine learning task in one of the deep learning frameworks. Suggested programming languages: Python.

One branch of deep learning deals with generative models, i.e. how to generate new data that is similar to the properties of the training data. One such example is the simulation of possible future (e.g. what will the the next frame in a video), or how to create new faces from celeb images (https://www.youtube.com/watch?v=XOxxPcy5Gr4). The task of the student is to learn about Generative Adversarial Networks (GAN) and conduct an individually chosen machine learning task in one of the deep learning frameworks. Suggested programming languages: Python.