utkarshmttl

Utkarsh Mittal

I am a Machine Learning enthusiast and have previously interned at various places in the same domain, most recent of them being my internship at Institut Pascal (CNRS), France. Here, I worked on automatic segmentation of liver vessels from CT images using deep learning and achieved a dice-coefficient of 88% which beats the current state of the art in the same. My mentor and I are currently in the process of writing a research paper for the same with the intent to present at MICCAI 2019. This internship gave me an opportunity to work in a full-fledged research setting, interact with experts in the field of machine learning and healthcare, and provided me with international exposure.

I have also undertaken several ML projects throughout my college course, one of them being Diabetic Retinopathy Detection. A scientific paper related to this project was accepted in ICICCT 2018 and has been accepted for publication in Springer CCIS vol. 835.

I am passionate about applications of Artificial Intelligence as well as healthcare issues and want to do my part in shaping the future of medical industry by infusing it with data driven intelligence.

Being a part of a unique course (B.Tech in Information Technology and Mathematical Innovations at Cluster Innovation Centre, University of Delhi) which encourages hands-on learning by integrating 40+ projects over the course of 4 years into the curriculum, I am always on the lookout for opportunities to use my skills to solve real world problems. My strong programming, analytical and research skills enable me to take a penetrating approach while building projects and conducting research. My good academic credentials throughout school and college reflect ability to keep up with rigor of programs and demonstrate commitment. My projects in the fields of Artificial Intelligence, Machine Learning, Data Science, Internet of Things, Android app development prove that my ideas are backed by the skills to execute them and demonstrate my prowess in IT. My internships at DRDO (2016) and NIC (2017), both under Ministries of Government of India, further bolster the aforementioned points, and provided me with time-management, communication, collaborative and research skills.

I have also personally mentored a student for an Android application project (eModules - https://github.com/utkarshmttl/eModules) as part of the CMoC program (https://github.com/clusterinnovationcentre/CMoC). Emodules, built for the purpose of digitizing question banks, is an android application that enables the user to practice offline from a set of questions, flag them and analyse his performance.

Since my first year, after being inspired from my first hackathon, I have been a part of several self-hosted mini hackathons with a group of close friends, where we try to complete some projects, catch up on piled-up works, and build epic stuff. An example of a 12 hour project, Voice Controlled Home Automation System, can be seen at https://www.youtube.com/watch?v=j2n5zNgveUE&t=34s.

As External Affairs Manager and then later the Convenor (Head) of the college’s Computer Society, my efforts have been monumental in establishing industry relations, inviting guest speakers, organising technical fests & hackathons and promoting peer-to-peer learning workshops. These activities speak for my leadership qualities, time-management and communication skills. I want to utilise these skills and eventually make an impact for the betterment of the society.

When I am not trying to make computers more intelligent, I travel (checked off 9 countries from my wishlist yet), read (high fantasy, fiction) or binge-watch. I am also an amateur pianist and guitar player. I also love ping-pong.

Projects

"Not HAL"

"Not HAL" is an intelligent surveillance system, with Artificial Intelligence (AI) backed anomaly detection technology.Keras

Skills

Python
PHP
Java
JavaScript
Machine Learning

Experience

  • CNRS