State-of-the-art Deep neural networks (DNNs, also known as Deep Learning) have had a transformative impact across many tasks, yet this improvement typically can only be achieved by using hundreds of thousands (ideally millions) of labeled data samples. This is due to the fact that modern-day large scale DNNs contain millions of trainable parameters. In many tasks, collecting this labeled data is either difficult or impossible. For example, segmented medical images can be produced by a skilled human annotator, yet doing this for a significant number of images is very expensive and time consuming. The aim of this project is to develop self-supervised and semi-supervised learning methods for training DNNs with only a handful of labeled samples. Although, the methods developed in this project will be of general purpose, so that they can be applied to any domain such as image, text or speech, the main focus of this project will be on the application of these methods to Drug Discovery.

2022

2025