Arushi Sharma's Projects
:sparkles: Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com
This project trains a few thousand names from 18 languages of origin and predicts which language a name is based on the spelling. It uses a character-level LSTM model to predict the next character. The model reads words as a series of characters and outputs a prediction and a βhidden stateβ at each step, feeding its previous hidden state into each next step. We take the final prediction to be the output, i.e. which class the word belongs to.
It contains all the basic code to start with the computer vision learning
This project does analysis on confirmed, death, and recovered cases of COVID-19 across the world and predicts the death of patients. It also predicts the spread of covid-19 in USA using SIR model.
Includes the code for accessing AWS services through terraform
We will be doing multiclass classification using Pytorch
The project does exploratory data analysis and uses multiple forecasting models to forecast grocery sales for next 15 days for a grocery store.
:zap: Dynamically generated stats for your github readmes
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Image Segmentation and clustering on handbag images to find color attributes for Handbags
This project explores image classification using PyTorch on the CIFAR10 dataset. The model has been trained using Convolutional Neural Network.
This repo contains mini projects in Information Retrieval. Covers indexing, document ranking, web crawling, page ranking, and evaluating different models
Contains the implementation of ML algorithms
This project helps to identify the classes present in the unstructured text of social media and tags the tokens as person, location, group, creative-work, product and corporation.
Object detection with real time video streaming from Kafka
contains small projects in R
Spam Classsification of Emails