Ram Ramrakhya Information Technology Undergrad, Researcher & Developer

I am a Graduate B.Eng. student from Pune Institute of Computer Technology. Currently, I am working as a Software Developer at InMobi. I am a problem solving and deep learning enthusiast. My research interests are at the juncture of software engineering and AI, solving problems which lie at the intersection of Computer Vision, Machine Learning and Natural Language Processing and I am always on the lookout for opportunities to learn more and work on exciting projects in this field. I am an active Open Source Contributor at CloudCV, an Open Source organization. I also actively work on Fabrik, an open source project aimed at lowring the barrier for getting started with deep learning.

Profile Pic

Fabrik - A Collaborative Neural Network Editor

Utsav Garg, Viraj Prabhu, Ram Ramrakhya, Deshraj Yadav, Dhruv Batra, Harsh Agrawal

SOSP'19 Systems for ML Workshop, (Accepted)

The paper presents an online neural network editor that provides tools to visualize, edit, and share neural networks from within a browser. Fabrik provides a simple and intuitive GUI to import neural networks written in popular deep learning frameworks such as Caffe, Keras, and TensorFlow, and allows users to interact with, build, and edit models via simple drag and drop with powerful collaborative features to enable users to iterate over model design remotely and at scale.




Publications
  • June 2018 - Current
    InMobi

    Software Engineer 2

    Bangalore, India

    Working on implementing content personalisation system, incremental caching layer to optimize latency and developing analytics data pipelines for data querying platform.

  • March 2019 - August 2019
    Google Summer of Code '19

    Mentor, CloudCV

    Bangalore, India

    Mentoring students for CloudCV, helping them develop features for the project during Google Summer of Code 2019.

  • October 2018 - January 2019
    Google Code-in

    Mentor, CloudCV

    Bangalore, India

    Mentoring students for CloudCV, helping them with various development problems, leading to the successful completion of over 40 tasks.

  • April 2018 - August 2018
    Google Summer of Code '18

    Student Developer, CloudCV

    Bangalore, India

    Worked on and currently maintain Fabrik, an open-source web application to collaboratively build, visualise and design neural networks.

  • January 2018 - May 2018
    InterviewBit

    Software Engineering Intern

    Pune, India

    Worked on designing and implementing SQL programming language judge and dashboard for interview pipeline on the InterviewBit platform.

  • October 2017 - March 2018
    Hackerearth

    Problem Setter

    Pune, India

    Worked with hackerearth for designing competitive coding problems.

  • July 2017 - May 2018
    NVIDIA

    System Engineering Intern

    Pune, India

    Worked on designing automated test suites for NVIDIA’s video encoders.

Experience

Fabrik

An open source web application to collaboratively build and visualize neural networks with a simple drag-and-drop interface.


Conditional VAEGAN

A simple extention of VAEGANs that employs label conditioning in additional to produce high resolution and high quality generated images. By adding an auxiliary classifier to the discriminator of a VAEGAN, the discriminator produces not only a probability distribution over sources but also probability distribution over the class labels.


EvalAI

EvalAI is an open source web application that helps researchers, students and data-scientists to create, collaborate and participate in various AI challenges organized round the globe.



Glance Recommender

A content recommendation system built using an ensemble of LightGBM and Deep + Shallow Neural Network for personalized content delivery. Model uses custom user & content features to rank the content based on past interactions on Glance app.


Humpback Whale Identification

A Siamese Neu​ral Network model designed to classify whale species using whale fluke images. Problem involved classifying whale fluke to one of 5005 categories with imbalanced data.


iMet FGVC'19 Challenge

Built a Squeeze-and-Excitation Network to build a multi-label classification model (1000+ classes). Trained using Focal loss & threshold search from pruned search space figured out by heuristics gathered from data analysis.



FlappyBot

A bot designed to play the game FlappyBird using neural network, the bot learns to play the game and gradually improving using genetic algorithm.


Thorax Disease Classifier

A deep neural network designed for identification of thorax diseases from chest x-ray images using transfer learning on VGG-16.


Net-Traffic

A network traffic classification tool designed using libpcap and python which uses deep packet inspection and machine learning techniques to classify network traffic.


Projects
  • August 2015 - June 2018
    Pune Institute of Computer Technology

    Bachelor of Engineering in Information Technology

    GPA - 4.00

  • August 2012 - June 2015
    Government Polytechnic Jalna

    Diploma in Computer Engineering

    Class Rank: 1st (All 6 semester)

    Passed with an aggregate of 89.03%

Education