I’m recent graduate from SRM University. Passionate about dealing with real world problems using Deep Learning. I’m looking for an opportunity to work in the field of Artifical Intelligence, preferably the one that expands current horizons of knowledge and keeps me on toes for perpetual exploration of implied potential
ZS is a management consulting and technology firm focused on transforming global healthcare and beyond.
Oct 2021 - Feb 2022, Chennai, India
Mentorship Programme led by University Alumni to teach how to do researh in field of Deep Learning
Team SRMSAT is a club of students who have interest in space technology. They have build satellites and launched to space.
Camber Racing is official Formula Student Combustion team of SRM University focused on building autonomous F1 cars and competing globally.
It composes style over content image. Programmers can play around with hyperparameters and visualize the transfer of style, style layers, content layers
Created AI programming language system using which you can program bots and make them do tasks like fight, resource collection, base creation. Pygame is used for creating the frontend of this board game.
Deep Learning model which uses the combination of Computer Vision and NLP to generate one line summary of the image, describing what it sees.
Quick and responsive Chat App in Flutter with google authentication and feature to send photos, gifs and stickers to other Qmates
Clima displays all the relevant environmental conditions of city user searchers. Flutter framework has been used to build this App
The System outputs a sequence of digits (0-9) inclusive one at a time, which user has to imitate from starting by tapping the keys on the keypad until the user tap the wrong key at some point.
Read many research papers to tackle imablanced dataset of heart patients of a hospital. Used SMOTE, Isolation Forest, PowerTransformer like methods to get better representation of underlying concept. XGBoost gave the best result of 89.9% accuracy.
A library that progressively updates the strength of augmentation (e.g.brightness, rotation) and applies it to batch of images for Self-Supervised Learning task. It is capable to work both on GPU and CPU due to kornia library backend. Along with this library, there is also the code for training models using ProAug which is written keeping in mind the Design Patterns.
B.Tech in Computer ScienceCGPA: 9.38 out of 10Extracurricular Activities
| ||
2017-2018 Senior Secondary School (X)CGPA: 9.2 out of 10Extracurricular Activities
| ||
With increase in unstructured data everyday, learning underlying structure of data has become rather important compared to the alternative of manually labelling data which is very costly. The primary goal of self-supervised learning methods is to capture the fundamental representations of data regardless of labels. In a contrastive learning setting, we have created a curriculum augmentation framework and trained a dual network with the help of that framework
I took this course with the intent to make base for Multi Agent Systems but ended up with realization that Game theory is ubiquitous and how its impacting our daily lives. This course taught me to understand the algorithmic aspects of game theory about recent developments in the field along with Mechanim Design which is useful to understand how to design our own game.
The course gave me indepth knowledge about the Cloud systems like kubeflow for machine learning inference along with technical understanding of GPU architectures. With that they ended up by focuing on industry standards for writing Deep Learning programs that execute on Multi-GPU settings and how we can scale out ML systems.
I had always been less passionate about App and Web development until I came across this course which intrigued me to take a deep dive into the field. Fascination for the same helped me to build my Chat app using firebase and gave me realization how the union of App Dev and Deep Learning can impact world around.
Starting from the basics of natural language processing I learned about word embedding techniques and ended up building applications that perform question-answering and sentiment analysis, created tools to translate languages and summarize text, and even built a chatbot.
Got introduced to the basics of Markov Decision Process, exploration and exploitation tradeoffs, value functions, dynamic programming use in Reinforcement Learning and understand thereof from algorightmic point of view.
I’m using the learnings of this course till date in every project. It helps me to write modular and scalable code. Getting to know about Command pattern, Decorator pattern and many more has been best part of learning to write better code
This course gave me in-depth introduction to golang programminng language. Made a Lexer in golang for new programming language.
This course fascinated me to the field of Deep Learning for Computer Vision applications. While being theoritically heavy it also had hands-on in PyTorch. I learned about Explainable AI, LSTM, Transformers, Self-Supervised Learning, Zero Shot Learning and many more.
