My major research areas of interest are :Machine Learning
In recent years, tremendous progress has been made in the field of Machine Learning with advancements both in theoretical and applied research. The advent of new applications has led reseachers to work on areas that need theoretical development, and theoretical ideas have demonstrated why some applications have become attractive. I was attracted to Machine Learning due to this intricate interplay between theory and application.
With the advent of technology, large data sets are being generated in almost all fields - scientific, social, commercial - spanning diverse areas like physics, molecular biology, social networks, health care, trading markets etc. Therefore, it has become imperative to develop algorithms which can process these large data sets in minimum time in an online and distributed fashion. I am interested to develop online tractable algorithms for Bayesian learning. I am also interested to explore theoritically why some algorithms work better than others.
The primary focus of our research is to enable the principled study of critical visual tasks with natural stimuli. Rather than attempting to develop a general model natural stimuli, we narrow the problem by focusing on the properties of natural stimuli that are most useful for particular tasks. We develop tools to enable rigorous mathematical characterization of task-relevant properties of natural stimuli. These tools help generate principled, quantitative hypotheses about how visual information should be ideally processed.
I started working in the field of Computational Neuroscience when I visited University of Pennsylvania in 2015. All of my work in this area is in collaboration with Prof. Johannes Burge.