Hi! My name is Deep Chakraborty and I am currently a Master's student in the Computer Science department at UMass Amherst.
My primary interests are in Deep Learning and Computer Vision. I am currently working on efficient face detection and verification algorithms using object detectors like Faster R-CNN. I also did a project on Semantic Segmentation in images for my Computer Vision class in which I used Dilated CNNs and it achieved near state-of-the-art accuracy on the Stanford Background Dataset.
In the past I've worked on dynamic kernel based Support Vector Machines and Deep Learning for birdsong recognition and embedded computer vision for robotics. Apart from applied machine learning research, I'm also interested in developing novel algorithms and architectures for machine learning. My aim is to enable intelligent reasoning in machines by drawing analogies from human reasoning process.
Apart from my academic interests, I enjoy listening to classic rock music, playing guitar, and cooking!