Data Science Group
IIT Roorkee

A student organization driving innovation via Machine Learning.




Accurate Prediction of COVID-19 using Chest X-Ray Images through Deep Feature Learning model with SMOTE and Machine Learning Classifiers

One of our members worked on COVID-19 predictions based on Chest XRays applying various Machine Learning algorithms. The research work received media recognition.


Understanding Graph Attention Networks (GAT)

GAT introduces a mechanism to attend over neighborhoods' features and weigh different nodes accordingly.


Kaggle Days

DSG in collaboration with E-Summit IIT R organizing Kaggle Days.


Visual ML

Interactive Visual Machine Learning Demos. Machine Learning in the browser powered by TF JS.


This project reproduces the book Dive Into Deep Learning (, adapting the code from MXNet into PyTorch.

Graph Representation Learning

Implementation and Explanation Graph Representation Learning papers involving DeepWalk, GCN, GraphSAGE, ChebNet and GAT.

Reinforcement Learning 2048

This project builds on a demo for playing the game 2048 using Reinforcement Learning.

Sarcasm Detection using BERT

Implementation of BERT based Sarcasm Detection Classification model using Tensorflow.

Adversarial Lab

This project builds on a demo for several Adversarial Attacks on ImageNet Classifier Models.

Number Plate Detection

This is a step towards automating the vehicles entering IIT Roorkee campus using state of the art Deep learning & Computer Vision.

Eye In The Sky: Image Segmentation Challenge Inter IIT 2018

Winning Solution in the Inter IIT Tech Meet 2018 Machine Learning Challenge, "Eye In The Sky".

Visualizing Loss Functions

Visualising different loss and optimisation functions using Autoencoders.

Neural Style Transfer

Implementation of Neural Style Transfer described in the paper by Gatys

Beginner Friendly Project: Traffic Sign Classification

Using GTSRB dataset to build a CNN based Traffic Sign Classifier.

Visit Cerebro, our competition portal.