• Hello World

    Work

    Currently, I am working as a Machine Learning Scientist at Cisco Innovation Labs.

    My background is in Deep Learning, NLP and Time Series Analysis, among other things.

     

    I am a hackathon junkie and love to build new things from scratch. You can check out my hackathon projects here.

     

    Always looking to collaborate with awesome folks to explore a domain, identify problems and build quantifiable solutions. Please reach out!

  • News!

    Paper in CoNLL 2016

    Our paper titled Adapting Event Embedding for Implicit Discourse Relation Recognition was accepted to appear at The SIGNLL Conference on Computational Natural Language Learning (CoNLL 2016) Shared Task held at Berlin, Germany from August 11-12, 2016.

    Hack Princeton 2016

    We got 4 awards: Most Launchable Product award sponsored by Dorm Room Fund, PrincetonPy / PICSciE Prize for Every Day Data for Tomorrow, Best Mobile App award, Best Use of Data Visualization award for our product EyePhone (More details here)

    HackIllinois 2016

    We got 3 awards: First Place Prize, Best Microsoft Hack and Microsoft's Best use of Azure for our product NeuroDoc (More details here)

    PennApps XIII

    We got the "Best Hack for Health Route" award for our product DataDoc (More details here)

    BostonHacks 2015

    We got the First Place Prize for our product WhatsUpDoc (More details here)

    Paper in ACL 2015 Main Conference

    Our paper titled "Reducing Infrequent-token perplexity via variational corpora" was accepted to appear at the Association of Computation Linguistics (ACL) 2015 Main Conference held at Beijing, China from June 26 to June 31, 2015.

    Thanks to Yves Xie for this collaboration.

    Undergraduate Thesis at Northwestern University

    I got an offer to work as a research intern at Northwestern University, Evanston IL USA under the supervision of Prof. Ankit Agrawal of Department of Electrical Engineering and Computer Science, Northwestern University, USA. 

    This will be part of my Undergraduate Thesis. 

    Intelligent Diabetes Management Project

    The work I did as a Research Intern at University of Alberta, Edmonton got showcased in the form of a TV interview and a newspaper article. More here:

    Story
    Newspaper Article
    Television Interview

    IBM Winter School

    I got selected for IBM Big Data Analytics and Cognitive Computing winter school to be held at Bangalore on October 9th and 10th, 2014. IBM has been kind enough to provide a travel grant to attend the Winter School too.

     

  • Publications

    Maria Leonor Pacheco, I-Ta Lee, Xiao Zhang, Pranjal Daga, Di Jin, Ayush Parolia, Dan Goldwasser

    SIGNLL Conference on Computational Natural Language Learning (CoNLL )2016 Shared Task

    Yusheng Xie, Pranjal Daga, Yu Cheng, Kunpeng Zhang, Ankit Agrawal, Alok Choudhary

    Association of Computation Linguistics (ACL) 2015 Main Conference

    Pranjal Daga, D.P. Acharjya, J. Senthil, Pranam Daga

    3rd International Conference on Soft Computing for Problem Solving (SocProS 2013)

    AISC Series of Springer

  • Research Projects

    THIS LIST IS WAYYYYYYY TOOOOOOOO OLDDDDD!

    Most of my projects are listed on LinkedIn: Click here

    Benchmarking Deep Learning Tools

    Supervisor: Prof. Alok Choudhary, Prof. Ankit Agrawal

    Compared various deep learning software packages like Torch, Theano, Caffe on different metrics (accuracy, timing, memory usage, etc.) for different deep algorithms.

    Understanding Climate Change: A Data Driven Approach

    UNDERGRADUATE THESIS

    Supervisor: Prof. Alok Choudhary, Northwestern University, IL USA

    • Extending the work of Ghosh et al to global and multi-climate model data.
    • Developing a parallel C (MPI) code that emulates the original MATLAB script.
    • Next goal will be downloading the massive climate precipitation NetCDF data from the servers.

    Exploring Deep Learning applications to fMRI

    Supervisor: Dr. Irina Rish, IBM T. J. Watson Research Center, Yorktown Heights, NY USA

    • Used deepnet package to learn a 3-layer Boltzmann machine for pretraining.
    • Dataset to be used: pain, schizophrenia, cocaine addiction.

    Intelligent Diabetes Management

    Supervisor: Prof. Russ Greiner, University of Alberta, Edmonton, Canada

     

    This research internship was fully supported by MITACS Globalink Fellowship Grant.

    • Developing a cross platform app Edmonton Automated Sugar Intelligence (EASI) which recommends insulin dose based on the patient's input and settings set up by his/her diabetologist.

    • Developed a tool which automatically adjusts the amount of insulin to be injected.
    • Modified T1DMS Simulator to use it with 20 in-silico patients.

    • Demonstrated that a supervised learning approach is better than certain reinforcement

      learning techniques like SARSA, Actor-Critic Model.

    MIT SANA Mobile: Protocol Builder

    Supervisors: Dr. Thomas Brennan, Massachusetts Institute of Technology; Prof. Senthil Jayavel, VIT University

     

    Sana is a standard-focused open-source end-to-end telemedicine system that facilitates the capture of medical data and physiological signals through a fully programmable work ow interface.

    • Built a database that contains rapid search and a training set for (future) automated A.I. classification of images, audio and video.
    • Constructed a web based protocol for Clinicians.
    • Worked on integrating SANA with OpenMRS (a Medical Record System) for portability.

    Machine Learning Approach for Detection and Supervision of Parkinson's Disease

    Supervisor: Prof. B.K. Tripathy

    • Developing an intelligent mobile application that collects patient input through tests (Gait,Handwriting, Speech, Tremors) and provides interactive feedback to patients and monitoring summaries for physicians.

    • Discovery of hidden relationships through unsupervised learning (clustering), leading to the identification of dierent Parkinson's disease variations.

    • Automated ranking of different inputs (attributes) by measuring their information content.

    • Used University of California, Irvine’s PD Telemonitoring dataset.

    "Deep" Recommendation System

    Supervisor: Prof. B.K. Tripathy

    • Proposed a ’collaborative’ deep learning model which tightly couples convolutional neural networks and probabilistic matrix factorization.
    • Better performance than Collaborative Filtering was shown using MovieLens dataset.

    "Learning" Personality from Social Posts

    Supervisor: Prof. B.K. Tripathy

    • Scrutinized linguistic content from Facebook, extracting keywords to analyze personality.
    • Used a linear SVM for classifying sex and ridge regression for predicting age.

    Adaptive GPS Algorithm using Djiktras Techniques

    Supervisor: Prof. Gayathri P.

    Designed a hybrid algorithm using Fuzzy Logic allowing user to incorporate information such as traffic levels, weather conditions and construction zones to find an optimal shortest distance between two points with the help of Djikstras Algorithm.

  • Implementation Projects

    THIS LIST IS WAYYYYYYY TOOOOOOOO OLDDDDD!

    Can't believe there is no hackathon project here.

    Check out my Devpost: Click here

     

    • Developed registration software for external and internal participants to register for events in graVITas'13- An International TechnoManagement fest at VIT Vellore, India.

    • Fixed a number of bugs in the ocial graVITas website.

    • Tools Used: HTML, CSS, PHP MySQL, Javascript etc.

    Appreciated by Microsoft App Excellence Lab as a "Rockstar" app at the Windows 8 AppFest held at Bangalore, India.

    Also, Featured in the Top 500 Windows 8 apps.

    • Fastest way to take quick notes in the midst of doing other activities and share them.

    • Tools Used: Visual Studio using HTML, CSS, Javascript.

     

    • Played the role of a committer and wrote end-user documentation and cited examples.
    • Debugged the code and documented the whole development process.

  • Leadership

    zzzz Older list again. Check out my LinkedIn: Click here

    Social Chair, Intern Class of 2016 @ Adobe

    May 2016 - Aug 2016

    Senator, Purdue Graduate Student Government @ CS, Purdue

    Jan 2016 - Present

    Teaching Assistant / Partial Instructor CS182 @ Purdue

    Aug 2015 - Present

    Joint Secretary, IEEE CS @ VIT

    Jan 2014 - Dec 2014

    Coordinator, graVITas 2013 @ VIT

    June 2013 - Sep 2013

  • Contact Me

  • Reach Out!

    Feel free to contact me anywhere, anytime.

    Email

    Facebook

    LinkedIn

    Twitter

    Google+