I want to have a career in data science and develop cutting edge products that will change our society. I am confident in my skills and abilities to come up with interesting ideas for achieving the desired goal. I am committed to continuous learning and developing my skills.
Resume Email
In my final Year project We had to build a ML system which detects deviations and provides corrective actions. This was an industrial project developed for Fransha Pharma LLP a pharmaceutical solution provider.
This app Uses the proximity sensor to capture Screenshots. When the user waves his hands over the screen the app captures and stores screenshots. App had 1000+ downloads
View App
Silencer uses the proximity sensor of yor device to activate the silent mode. Since it uses the proximity sensor you don't have to touch the device physically. App had 100+ downloads
View App
In this web app one can apply any preprocessing steps by just a click of a button no need to write code. This app supports all basic nlp preprocessing steps needed to clean the text like removing stopwords , stemming or lemmatization users can choose between different stemmers, different stopwords dicts ect. The main goal of this app is to reduce the time takes writing boilerplate code . Check the github repo for a desktop version made using Kivy
The main goal of this project was to learn about the seq2seq architecture using different attentions mechanisms . I have tried to implement different attention mechanisms from scratch. In the end I ended up developing a simple gui and terminal app using which users can train the seq2seq model on different languages using different attention mechanisms. CheckOut the different attention mechanisms used by clicking on the notebook button.
The web app detects any toxicity, haterade or anything that shows negative emotion in the user's comment. Warning them about the negative emotions he/she may convey knowingly or unknowingly. This can also act as a filter for social media platforms where each post can be checked for toxicity before forwarding it helping reduce negativity
Recently I participated in JanataHack: Computer Vision Hackathon hosted by Analytic Vidhya. The aim of the competition was to create a binary image classifier that could differentiate the Non — Emergency Vehicles eg. private owned vehicles . from the emergency vehicles (police vehicles , ambulances, etc). Read Blog
The main goal of this project was to learn about different gans architectures and implement them in pytorch. I have also developed an simple web app using conditional gans in which users can enter any number (0 - inf) and the gan produces an image for it. This application of gans is quite interesting where in we can generate new data
The main goal of this project is to learn about the different stages (detection,extraction,classification) involved in the in the recognition pipeline and to try implement the classification stage from scratch.
The goal of this project is to implement decision trees, random forest , naive bayes etc only using numpy,this helps in understanding how different algorithms work internally.