Arsen Sheverdin
AI Master's student at the University of Amsterdam
arsen.sheverdin [AT] student.uva.nl
About
I am an Artificial Intelligence Master’s student at the University of Amsterdam, where I am currently working on my thesis on probabilistic deep learning methods for continual learning with Dr. Eric Nalisnick at the AMLab .
My main research aspiration is the development of safe and robust agents capable of (1) not only learning but also “knowing” what they do not "know”, and (2) adapting to the distribution shifts of the incoming data and learning continually. Such models would be of high relevance in the contexts of high-risk scenarios in fields such as medicine, autonomous driving, and robotics, where the reliability of the agents is of paramount importance.
I am especially keen on Bayesian methods for deep learning with a focus on uncertainty quantification, continual and active learning, and AI safety.
Bio
I obtained my undergraduate degree in Physics with Mathematics minor at the Nazarbayev University. During my undergraduate, I was fortunate enough to receive the Yessenov Foundation scholarship to conduct a research visit at the Cornell University, where I worked on developing deep learning methods for inverse design for nanophotonic structres, under the supervision of Dr. Francesco Monticone . As an undergraduate, for two years I also was a Research Assistant at my university's Physics department, where I studied the nanophotonic structures and their optimization under the supervision of Dr. Constantinos Valagiannopoulos
Publications
Most recent publications on Google Scholar.