This talk by Franz Papst will be taking place online on June 19 from 15:00-16:00 (CEST/UTC+2).
To join the talk click here
Abstract:
The last decade saw the rise of deep learning. The abundance of available data and ever-increasing computational power pushed the boundaries of machine learning. Deep learning has been applied in many different areas and achieved state-of-the-art performance in many of them. However, privacy concerns are hindering the adoption of deep learning in fields like medicine or finance, even though it also could make a positive impact in these fields.
This talk will present some methods for processing data in a privacy preserving way and show how it is possible to learn something about a given dataset without learning too much about the individuals in this dataset.