The Iris Classification CI/CD Project is machine learning application that classifies iris flowers using multiple algorithms, integrates a CI/CD pipeline for seamless deployment, and employs Docker…

A complete pipeline for training and evaluating models on the MNIST dataset using knowledge distillation. It involves a teacher model, a regular student model, and a distilled student model.

System that uses a hybrid of Genetic Algorithms and Neural Networks to optimize resource allocation under constraints. It features real-time solution visualization, auto-saving of results, and conf…

In this project, I applied advanced deep learning techniques for model optimization, including adaptive learning rates, data normalization, and tuning on a noisy sine wave dataset. SGD and Adam opt…

In this project, I implemented a PyTorch-trained MNIST digit classifier and hosted it as a REST API using the Gin framework in Go. Users can upload an image and get the predicted digit with probabi…

Building on REINFORCE's foundation, this project creates more stable RL agent for grid navigation by adding PPO clipping and KL penalties. The enhanced algorithm helps an 8×8 grid agent learn effic…

Building an LLM with RLHF involves fine-tuning using human-labeled preferences. Based on Learning to Summarize from Human Feedback, it uses supervised learning, reward modeling, and PPO to improve …

"ImitatingYAKE" is a Python-based system for extracting keywords from HTML documents using tokenization, n-grams, and frequency analysis. Inspired by YAKE, it ranks keywords based on position, freq…

ChromaQuery is a Retrieval-Augmented Generation (RAG) system that processes, stores, and queries PDF documents. Using ChromaDB for vector storage and Groq LLM for generating query responses, it eff…

FastAPI-based GraphQL service that benchmarks multiple classification models, providing real-time performance metrics like accuracy, precision, recall, and F1-score.

iBeer.ai is a smart platform that offers detailed beer profiles and personalized recommendations through simple label scanning. Using advanced technologies like computer vision and NLP, it provide…

Yume Waifus is a playful web app that generates anime-inspired waifu images and features a conversational AI chatbot, offering both SFW and NSFW interactions based on user preferences

This project creates a Grid World game in Python, where the player navigates a grid to reach a goal while avoiding monsters, and the agent uses the A* algorithm to autonomously move towards the go…

Schedly is a FastAPI-based project that provides APIs for extracting information from emails, analyzing sentiment, generating responses, and creating calendar events in ICS format. It leverages Gro…

FlirtyHuh is a fun flirt bot that generates witty and charming responses using a custom-trained T5-small model. It features a user-friendly front-end built with HTML, CSS, and JavaScript for seaml…

FastAPI-based web application with user authentication features. It leverages SQLAlchemy for database management, Jinja2 for templating, and serves static files.

DocQuery AI An AI-powered document querying tool enabling users to interact with PDF documents using natural language queries. Built with Python, FastAPI, and LangChain (Groq API), it features inte…

Exploring LLMs with interactive notebooks.

OpenStreetMap data and the A* algorithm to calculate and animate walking routes. It allows users to explore multiple paths between two points, providing an interactive way to visualize route networks.

ParmaQA.ai is an advanced QA system that combines a Retrieval-Augmented Generation (RAG) pipeline with LangChain, FAISS, and FastAPI to deliver accurate answers. It features an efficient backend f…

A project designed to deploy and run Azure Functions using Python, enabling serverless computing capabilities. This project includes a machine learning model for predictions, integrated with a REST…

Iris Classifications is a web application that leverages machine learning with Flask and FastAPI to classify iris flowers into species based on user-provided input features, ensuring a seamless exp…

This repository focuses on reproducing results from notable machine learning and AI research papers by implementing their methods, models, and experiments. Each project includes detailed documentat…

This repository integrates Groq with LangChain to create an advanced response generation system. Leveraging Groq's high-performance computing and LangChain's flexible framework, it handles tasks li…

This repository is a collection of projects, experiments, and notes documenting my journey through reinforcement learning. It includes code implementations, research summaries, and practical exerci…

Preparation for interview