I am a PhD student in Computer Science at Northeastern University, advised by Prof. Robert Platt Jr., and Prof. Ennio Mingolla. I am a member of the Helping Hands Lab.

My main interest is in the field of Motion Prediction. In particular, I am interested in applying computer vision and deep learning to the problem of predicting motion.

Previously, I was a visiting research scholar at The Battelle Center for Mathematical Medicine, The Research Institute at Nationwide Children’s Hospital, which is a part of Department of Pediatrics, The Ohio State University College of Medicine. At OSU, I worked jointly with Prof. Andrzej Kloczkowski, Professor of Pediatrics, The Ohio State University and Principal Investigator, Battelle Center for Mathematical Medicine and Prof. Irina A. Buhimschi, Director, Center for Perinatal Research and John E. Fisher Endowed Chair of Neonatal and Perinatal Research.

In May 2017, I completed my undergraduate degree from Shiv Nadar University, India in Computer Science and Engineering with a minor in Data Science. I completed my undergraduate thesis at The Center for Perinatal Research, jointly with Dr. Nathalie L. Maitre (Director, Neonatal Follow-Up Programs, Principal Investigator, Center for Perinatal Research and Associate Professor of Pediatrics at The Ohio State University), Andrzej Kloczkowski and Irina A. Buhimschi on Development of a Neonatal Tactile Connectome using Graph Theory for the Prediction of Neurobehavioural Adaptation in Early Childhood. The project is nicknamed Baby Connectome. During the course of my undergraduate studies, I squeezed in three visiting scholar positions at The Ohio State University (Jul 2015, May 2016 and Jan 2017) and one Software Engineering Internship at HCL, where I worked on developing a Hostel Management System.

I am interested in the combined studies of Neuroscience and Deep Learning, where I wish to apply my learnings from the brain to the effective designing and theoretical understanding of stronger neural networks, which are powerful in terms of processing but with a decreased cost, something similar to how the human brain works and how this field of neural networks started; highly motivated by Rossenblatt’s Perceptron.

So far, I have been able to patent 3 of my inventions, namely, Biomolecule based Data Storage System (PCT/IB2015/057964), Method of Data Compression and Decompression (PCT/IB2016/054294, 83% more efficient than the current best, analogous to non-neural network based autoencoder, more can be found in this paper) and Secure multi-level electronic authentication techniques (Indian patent office reference 201711022812).

On fun side, I occasionally blog here and here, tweet and publish my codes. My old site can be found here.
I am also a fan of strong, powerful, cult, classic and realistic cinema.
A copy of my most recent CV can be found here, and resume here (PS: they are seldom updated)