Budapest Artificial Intelligence Meetup - January

Preliminary agenda:

* József Németh (Senior Machine Learning Engineer) - Generative Modeling

While deep learning brought improvements in a lot of areas of computer science, generating realistic data samples is a challenging task that really requires the high representational capability of deep neural networks. Using the recently developed techniques, we can generate realistic samples like high-quality human voice or high-resolution images. At the same time, using generative models we can also learn meaningful representations of the data, that can be then used to solve other tasks, such as classification. In my presentation, I will talk about the basic concepts of generative modeling and the two most popular methods: the Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) and some of their variants. Finally, I give an overview of the wide variety of application areas. These include examples that bring quality life improvements and also about those that raise serious ethical questions about the shiny new world.