This project explores how GPT2 can be used as a sentiment classifier, and how we can use adversarial noise to cause incorrect sentiment classifications. The adversarial examples are created using gradient ascent.

• View Code

This project contains the implementation of a language model using n-grams. Evaluated by the it's score and perplexity. It generates sentences based on probability and utilizes the Shannon technique.

• View Code

This project explores enhancing autonomous vehicle decisions: From classical planning to advanced RL. Value Iteration to DQN for adaptability, memory efficiency, and scalability in multi-agent scenarios.

• View Code

Developed a Java image processing app with meticulous optimization for superior performance. Features seamlessly integrated CLI and GUI for modular, user-friendly experience.

• View Code

This repository showcases my Pix2Pix Generative Adversarial Network (GAN) implementation, delving into image-to-image translation through adversarial training.

• View Code

This model detects whether a person is wearing a face mask or not. It was built using DETECTO. The main.py file is for running this model on images.

• View Code

This model is a state-of-the-art object detecting model built using Tensorflow's object dection API. A retrained Faster RCNN is used to maximize performance and accuracy.

• View Code

This is your last chance. After this, there is no turning back. You take the blue pill - the story ends, you wake up in your bed and believe whatever you want to believe. You take the red pill - you stay in Wonderland and I show you how deep the rabbit hole goes.

• RED PILL