Implementing an LLM from scratch block-by-block using PyTorch

Understanding of the news data via clustering

Implemented Divide and Conquer-Based 1D CNN approach that identifies the static and dynamic activities separately. The final stacked model gave an accuracy of 93% without the test data sharpening p…

Detailed sentiment analysis (overall and aspect based sentiment analysis) on major Singapore attractions.

This repository contains all my submissions for my graduate program at IIIT, Bangalore

This repository contains the image classification followed by semantic segmentation of Chest X-Rays to detect a clinical condition called Pneumothorax.

A graph mining problem where the task was to predict a link between the given nodes. Engineered different features like Jaccard Distance, Cosine-Similarity, Shortest Path, Page Rank, Adar Index, HI…

The problem that this case study is dealing with predicts the location that a user is most likely to book for the first time. The accurate prediction helps to decrease the average time required to …

This repository is doing sentiment analysis ( review analysis ) on Amazon Food Dataset

This challenge is about detecting the question when posted by the user on the Quora portal as duplicate or not .

In this repository, there are two python files having different Multi Layer Perceptrons (MLPs) and Convulational Neural Networks (CNNs) models built from scratch on the MNIST dataset.