I am a fourth-year Ph.D. student in computer science at the University of Wyoming. Broadly speaking, my research interests are NLP, Machine learning, Deep learning, and the intersection of AI and medicine. Before coming here, I obtained a BSc and MSc in electrical and biomedical engineering, respectively.
My current project is about utilizing the explainability of neural networks to boost generalization. The idea is by blurring/removing those salient regions in our images, force our model to focus on other/specific visually important features. Finally, the idea is to use this method as a state of the art data augmentation method that decreases overfitting and leads to better generalization.
Last summer(2022), I was a machine learning research intern at Bosch working on explainability and use of transformers for loclizations of objects.
In summer 2020 I was an intern at NCAR and High Altitude Observatory group. In that project, considering the Sun's constant effect on Earth’s space environment, we were interested to study and measure magnetic fields on the Sun. We explored the use of clustering techniques on maps of physical quantities from polarimetric inversion codes, as well as the raw Stokes spectra, intending to find a meaningful relation that can be used in place of the prohibitively computationally expensive inversion. My presentation for this project is available here.
During my master's, I did multiple projects at the intersection of medicine and machine learning. In one project we tried to make a trade-off to build a model for survivability of breast cancer with the potential of being interpretable and having outstanding performance simultaneously. In another project, we build different models to be able to predict the outcome of traumatic brain injury using logistic regressions, support vector machines, and random forest.