Shri's repositories
Prompt-to-Song-Generation-using-Large-Language-Models
This project uses LLMs to generate music from text by understanding prompts, creating lyrics, determining genre, and composing melodies. It harnesses LLM capabilities to create songs based on text inputs through a multi-step approach.
Adaptive-Deep-Learning-for-Environment-Agnostic-Human-Action-Recognition
This repository dedicated to Adaptive Deep Learning for Environment-Agnostic Human Action Recognition. This project focuses on developing a robust deep learning system tailored for accurate identification and analysis of human actions across diverse environments, with applications spanning surveillance, security, sports, and fitness.
Multi-Agent-RL-in-Gridworld-Complex-Environments
MARL explores cooperation & competition in gridworlds. Batman & Robin team up (DQN, CQL, MAD-DQN, REINFORCE). Adversaries use MADDPG with CLDE for strategy.
A2C-Exploring-OpenAI-Gym-Environments-and-Enhancing-Actor-Critic-Algorithms-for-Optimal-Performance
This project provides a comprehensive understanding of reinforcement learning, focusing on Actor Critic Algorithms. It involves exploring the OpenAI Gym library, implementing the A2C algorithm from DeepMind's seminal paper, and enhancing the A2C algorithm for improved performance and stability.
CodeName-Detective
My GitHub Portfolio
CUDA_GPGPUs_Shared_Memory_Systems_PDP
CUDA GPGPUs Shared Memory Systems Parallel & Distributed Programming
Data_Mining
Projects Related To Data Mining
Deep-Q-Learning-Exploring-OpenAI-Gym-Environments-and-Enhancing-DQN-for-Optimal-Performance
This project provides a comprehensive understanding of reinforcement learning, focusing on Deep Q-Learning (DQN). It involves exploring the OpenAI Gym library, implementing DQN from DeepMind's seminal paper, and enhancing the DQN algorithm for improved performance and stability.
First_Principles_Of_Computer_Vision
Multiple Projects Related To First Principles of Computer Vision
Inverted-Index-DAAT-Python-Flask
This repository hosts a Python-based project that implements an advanced Inverted Index using a Linked List structure, and Boolean Retrieval. It leverages Flask to create a web application that allows users to perform Boolean queries through a Document-at-a-time (DAAT) strategy. Optimized for fast retrieval and efficient storage.
MPI_Hybrid_Distributed_Memory_Systems_NUMA_PDP
Parallel Algorithms for Distributed Memory Hybrid systems using MPI.
Neural-Image-Classification
Neural Image Classification repository, where cutting-edge deep learning models have been crafted and fine-tuned for diverse image classification tasks. Leveraging state-of-the-art architectures and innovative techniques, this repository stands as a testament to high-performance image recognition.
Neural-Machine-Translation
This GitHub repository houses an innovative implementation of Neural Machine Translation (NMT) using state-of-the-art sequence-to-sequence networks. The primary focus is on enhancing translation quality through progressively advanced architectural improvements.
NovelConvo-AI-Intelligent-Conversations-with-Literary-Companions
NovelConvo AI engages users in dynamic conversations about curated novels. With chit-chat and Q/A components, it's a literary companion delivering both entertainment and information. An immersive AI experience for novel enthusiasts.
portfolio
A modern static resume template and theme. Powered by Jekyll and GitHub pages.
Linear_Algebra_And_Numerical_Optimization
This repository provides implementations of various algorithms in linear algebra and numerical optimization.
OpenMP_Shared_Memory_Systems_NUMA_PDP
Parallel Algorithms for Shared Memory systems using OpenMP.
Reinforcement-Learning-for-Stock-Market-Trading-A-Case-Study-on-Nvidia-Stock
This project applies a Q-learning agent to develop a trading strategy that maximizes profit through stock trading. The environment is based on historical stock prices of Nvidia over the past two years, containing 504 entries from 02/01/2021 to 01/31/2023.
Robust-Pathfinding-Tabular-and-DeepRL-in-Deterministic-and-Stochastic-Grid-Worlds
This project explores robust pathfinding solutions using both tabular and deep reinforcement learning techniques in various grid world environments. The environments include deterministic and stochastic settings, each with unique reward structures and transition dynamics.