Giter VIP home page Giter VIP logo

Hey, I am Ruskin 👋

I am a Master's student at Stony Brook University. My research interests lie in the area of NLP and Reinforcement Learning. Currently I am working as a Research Assistant with the NLP group here at Stony Brook. Prior to this, I was a Software Engineer at PayTM, where I had a fun time developing APIs and user-facing services. I have an extensive background in ML, where my research work titled "Local and Global Context-Based Pairwise Models for Sentence Ordering" was published in the estemeed journal, Elsevier Knowledge-Based Systems. I have done many other internship and research projects in ML/NLP as well.

I love chatting and meeting new people so if you ever wanna get in touch drop me a message on LinkedIn

Skills

Here are a few things I've picked up along my learning journey.

Languages: Python(ML/NLP), Java(Web Development), C++(Competitive Programming)

ML Libraries: PyTorch, Hugging Face, Tensorflow, Scikit-Learn, Pandas

Research Work

"DeepCuts: Single-Shot Interpretability based Pruning for BERT"

"Local and Global Context-Based Pairwise Models for Sentence Ordering"

"Stability optimization of Actor-Critic(A2C) algorithm using adversarial autoencoder for autonomous driving"

"Malaria Detection and Classificaiton"

ruskinmanku's Projects

chatbot_nlp icon chatbot_nlp

An LSTM based model for answering questions related to retail products.

deepcuts icon deepcuts

This repo contains the code for the project done as a part of the course, CSE 538: Natural Language Processing. In this project, we apply interpretibility techniques like GradCAM and SmoothCAM as a way to measure importance of weights during pruning.

nlp icon nlp

:memo: This repository recorded my NLP journey.

normalizing_flows icon normalizing_flows

Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows

pairwisemodels4so icon pairwisemodels4so

Code accompanying the paper "Local and Global Context-Based Pairwise Models for Sentence Ordering"

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.