Students

Are you a student interested in doing a master thesis on deep learning? Feel free to contact me to discuss potential ideas. I always take time to discuss with students. Some topic suggestions are:

• Federated and decentralized learning
• Out of distribution generalization
• Deep learning for tackling climate change
• Using deep learning to understand social issues

Supervised master theses

• [2024] Tom Hagander and Eric Ihre-Thomason On the effect of similarity metric in decentralized deep learning, Lund University
• [2023] Emilie Klefbom and Marcus Toftås Decentralized Deep Learning under Distributed Concept Drift, Chalmers University of Technology
• [2022] Karin Bergdahl Impact of model architecture and data distribution on self-supervised federated learning, Lund University
• [2021] Noa Onoszko and Gustav Karlsson PENS: Leveraging Data Heterogeneity in Federated Learning, Chalmers University of Technology
• [2020] David Ericsson and Adam Östberg Adversarial representation learning for private speech generation, Chalmers University of Technology
• [2018] Henrik Arnelid Sensor modelling with recurrent conditional GANs, Chalmers University of Technology