I am a PhD fellow in Informatics at the University of Oslo, Norway. I have previously taken a MSc in Renewable Energy at Oldenburg University, Germany. My current work focuses on applying machine learning in smart grids. I participated in many energy informatics research projects and I am a Marie-Curie felloship alumnus.
Because GANs framework consists of two networks, a generator and a discriminator, we find it not easy to know which network and which part of that network contains the transferable features and hence parameter? Should we fine-tune or freeze the shared parameters? I tryied to answer these questions by showing empirical results of a series of experiments extended from Project 1 to for time series to images data. The results were presented in Confer Conference, the presentation link is below.
I contributed in “Medico automatic polyp segmentation challenge”. Polyps are one of the causes of colorectal cancer and early diagnosis of polyps by can lead to successful treatment. My contribution shows a use of GANs-based model to automatically segmenting out the polyps area within gastrointestinal images.
I teamed up with my 7-year-old daughter, Leen, to contest in MedAI: Transparency in Medical Image Segmentation Challenge. We had a lot of fun in making the computer to learn to segment medical images and explain how it came up with predictions. We also managed to submit a short working paper to Nordic Machine Intelligence open access journal. ! A main takeaway of this is that: (Model Accuracy + Model Explainability = Authentic Value). Here is our working paper and the code. Our team (called Leen) got an honorable mention too!!