Dynamic Scheduling Problem Python Solver with RL

Still work in progress This project focuses on exploring the research field of dynamic scheduling problems with RL, dealing with stochastic arrival of the new orders and tardiness cost function Main points: Developed the ’Environment’ class using object-oriented programming in Python to address a dynamic scheduling problem, enhancing system flexibility and scalability. Engineered a Reinforcement Learning (RL) agent complete with a customized learning algorithm to efficiently manage dynamic scheduling of orders, accommodating random arrival times and diverse cost functions such as earliness and tardiness.

July 1, 2023

Domain Adaptation for Egocentric Action Recognition

Github Repo This project focuses on advancing the field of Egocentric Action Recognition through innovative domain adaptation techniques. By leveraging RGB features extracted from the EPIC KITCHEN DATASET with a 3D-inflated network, we explore different domain adaptation methods to enhance generalization across various domain shifts. Our approach combines adversarial learning modules at different temporal aggregation levels with an attentive mechanism and Minimum Class Confusion loss, achieving significant improvements over baseline models.

March 10, 2023

EduQuery: your personalized learning companion

Github Repo EduQuery is an online learning platform leverages Language Learning Models (LLMs) to create a gamified educational experience. By integrating adaptive learning algorithms, it personalizes content delivery, ensuring that each learner’s journey is unique and engaging. The platform’s interactive challenges and reward systems are designed to increase motivation and enhance retention. With a focus on collaborative learning, users can connect and compete, fostering a community of learners. The use of LLMs not only facilitates language acquisition but also encourages critical thinking and problem-solving skills, making learning both fun and impactful.

October 29, 2022

Published Research on Modelling Ribosome response to nutrient shift

Github Repo For my Bachelor’s final project in Physics, I delved into the realm of Biophysics, embarking on a research journey to develop a novel model. Focused on understanding the response of specific Ribosome characteristics to nutrient shifts, our endeavor aimed to fill a crucial gap in existing knowledge. Through meticulous exploration, we unearthed a significant oversight in the prevailing model, which primarily addressed specific conditions rather than the broader scope.

July 10, 2021

Options Pricing calculator Library in C++ and CUDA

Github Repo The goal of this project was to write a fast and reliable library to compute the price of different Options built on stochastic-simulated stock paths, leveraging the computational power of GPUs and CUDA Main points: Developed a CUDA-based library for GPU-accelerated Monte Carlo simulations, achieving over 30× faster option pricing analyses for both vanilla and exotic options compared to CPU benchmarks. Leverage CUDA programming and financial modeling, ensuring rapid and accurate option valuation in high-performance computing settings.