Study Buddy - Major Project (DKN Implementation)

Overview

This repository contains the core Jupyter Notebook (Study_Buddy_DKN.ipynb) for the Study Buddy major project. The notebook implements a Deep Knowledge-Aware Network (DKN) designed to enhance content understanding and learning recommendations. By leveraging advanced Natural Language Processing and Machine Learning techniques, this project aims to process complex educational data and deliver highly contextualized insights.

Key Features

• Knowledge Graph Integration: Embeds external knowledge representations to capture rich, relational context between different study concepts.
• Advanced NLP Capabilities: Utilizes state-of-the-art language processing to parse, analyze, and map educational material.
• Explainable AI (XAI) Focus: Built with interpretability in mind, ensuring that the model's outputs and recommendations can be clearly understood and validated.
• Scalable Architecture: Lays the groundwork for continual learning implementations, allowing the system to adapt to new study materials over time without catastrophic forgetting.

Repository Structure

• Study_Buddy_DKN.ipynb: The primary notebook containing data preprocessing, knowledge embedding initialization, the model training loop, and evaluation metrics.

Setup and Installation

1. Clone the repository:

   git clone [https://github.com/TheJollyNaman/Study_Buddy_Major_Project.git](https://github.com/TheJollyNaman/Study_Buddy_Major_Project.git)
   cd Study_Buddy_Major_Project
   

2. Install the required dependencies. It is recommended to set up a virtual environment first: Bash pip install -r requirements.txt

(Note: Ensure your environment is configured with compatible versions of your preferred deep learning frameworks, such as PyTorch or TensorFlow, along with any necessary graph processing libraries). 3. Development Environment: This codebase is optimized for AI-assisted development workflows. Loading the project directory into tools like Cursor AI will allow for seamless data workflow management, prompt-driven refactoring, and easier debugging.

Usage

Launch the notebook using Jupyter or your preferred IDE:

  jupyter notebook Study_Buddy_DKN.ipynb

Follow the sequential cells to:

1. Load and preprocess the target dataset.
2. Initialize the semantic and knowledge-based embeddings.
3. Train the DKN model.
4. Evaluate performance and extract explainable insights.

Future Enhancements

1. Expanding the architecture to incorporate multi-agent LLM frameworks for dynamic, interactive student assistance.
2. Refining the extraction pipeline to support a wider modality of inputs.