The research interests of our group lie in the areas of machine learning, statistics, and signal processing. We are presently particularly interested in i) fundamentals of deep neural networks, ii) deep neural networks for solving inverse problems, iii) learning from few and noisy examples, and iv) DNA data storage and DNA as digital information technology.
- Deep learning: Deep neural networks have become highly effective tools for signal and image classification, generation, and reconstructing. We are interested in general in the fundamentals of deep learning, and have a particular focus on the intersection of deep learning and inverse problem including denoising, inpainting, and reconstruction of images from few and noisy measurements. I'm interested in developing corresponding algorithms and theory.
- Machine learning from few and noisy examples: We are interested in theory and practice of learning from few and noisy examples, and in robustness aspects of machine learning.
- DNA data storage and DNA as digital information technology: How can information efficiently be reconstructed from millions of noisy sequences? That question lies at the heart of an emerging technology that stores digital information long-term on DNA. We are interested in DNA data storage and in using DNA as in information technology more broadly, with applications in storage, computing, random number generation, and cryptography.
To get a concrete picture of our current interests, please check out our recent publications here at google scholar.