I am a Data Scientist at Dropbox.
I am interested in large scale data mining applied to AI, Cyber Security, & Healthcare.
From 2012-17 I was a PhD candidate in Information Science (currently on leave) at Cornell Tech, Cornell University advised by Prof. Ramin Zabih. During PhD, I built practical systems capable of producing significant impact in medicine & computer vision. Also during summer of 2016 I interned at Dropbox with Abuse Prevention team.
How can we analyze visual data?
In spite of recent advances in computer vision, there is a need for a platform to analyze & share visual data (images, videos). Deep Video Analytics is an open source distributed visual search & data analytics platform. In addition to letting users quickly load, annotate, index & search, Deep Video Analytics enables development of data-centric approaches to Computer Vision, by allowing reproducible research in collaborative and interactive machine learning.
How can we use large de-identified patient databases?
Today medical researchers can acquire de-identified data on millions of patients. Yet currently there are no systems that allow them to quickly explore & use this data while ensuring compliance with privacy requirements. Computational Healthcare platform indexes and aggregates data from millions of patient visits, enabling physicians and researchers to conduct high-impact medical research. Computational Healthcare has been used in several research papers.
Before PhD I completed Master of Engineering in CS from Cornell. During this time I interned at WebMD, and worked on several smaller projects. Such as community detection for Twitter, prediction of protocols for radiology orders. As an undergraduate I did research on prediction of physical properties of molecules.
Copyright Akshay Bhat, 2017. All rights reserved.