Interview Samuel Willingham
Samuel works as a joint Early Stage Researcher at Mid Sweden University and the French Institute for Research in Computer Science and Automation (Inria). His research topic is “Learning Algorithms for Inverse Problems with New Imaging Modalities“.
Tell me about your research topic?
Currently, I am looking at deep equilibrium models (DEQ) for image reconstruction. DEQ use math to facilitate learning for architectures that are based on repeated application of neural nets. In essence, this means that DEQ can help us train iterative procedures end-to-end. I am currently attempting to leverage the advantages of DEQ to improve current algorithms for image reconstruction.
One future topic I will look at is extending current theory on image reconstruction to novel imaging modalities like omni-directional images or light-fields. The advantages of using DEQ (i.e. lower memory-usage when compared to unrolled methods) may become even more relevant when applied to large data samples and higher dimensional data.
Tell me about yourself, your background?
I was born and raised in Stuttgart, Germany, and attained a MSc in Mathematics from the University of Stuttgart, where I wrote my thesis on learning with singular kernels. Before starting my position as an early stage researcher at Plenoptima and during my studies, I worked at the IT-consulting agency broker2clouds.
The concepts of machine learning are very intriguing to me and I think it is great to live in a time where knowledge is produced and shared at an unprecedented rate. I am ecstatic to have been given the opportunity to do research on fascinating topics and contribute to the advancement of knowledge and curiosity.
Why did you apply to the Plenoptima project?
Plenoptima is made up of people from different regions, life experiences and fields of knowledge. Because of that, Plenoptima seemed like a great opportunity to learn about new concepts related to machine learning and inverse problems and apply them to images while meeting interesting people.
What kind of expectations do you have for your research project and the upcoming network training?
I look forward to acquiring skills in research itself as well as the necessary abilities necessary to present and discuss research findings. My research topic is fascinating and I hope to share interesting results and contribute to scientific progress in as many ways as possible. Also, I am excited to meet people from different fields and learn from them.