Suche

Deep Learning for Data Augmentation


Description Health related databases are often too small for state-of-the-art deep learning. Further, it is timely and costly to collect new data.
Task In this thesis, the student(s) will explore state-of-the-art deep unsupervised data augmentation approaches to handle the lack of data for training machine learning systems.
Utilises Deep Convolutional Models, Generative Adversarial Networks.
Requirements Preliminary knowledge in Machine Learning, Good programming skills (e.g. Python, C++).
Languages English and German.
Supervisor Shahin Amiriparian, M. Sc. (shahin.amiriparian@informatik.uni-augsburg.de)