Probablistic AI, with focus on Bayesian Deep Learning, Uncertainty Quantification and their Applications in medical diagnosis, Segmentation and OOD detection. I also worked on Representation Learning using Self supervised learning methods.
Current project(s):
- Analyzing the Role of Model Uncertainty in Flourine-19 MRI Using Stochastic Gradient MCMC
- A probablistic approach to self-supervised learning using cyclic stochatic gradient MCMC
- Out of distribution detection using Bayesian deep learning models of 3D medical images in segmentation task (Master thesis)