This repository contains implementations of various machine learning papers from scratch using Python. The goal is to provide clear, well-documented code that helps in understanding the underlying concepts and algorithms presented in these papers.
Machine learning papers often present novel algorithms, architectures, or techniques that advance the field. This project aims to bridge the gap between theoretical concepts and practical implementation by providing code that closely follows these papers. Each implementation is written in Python mainly(if they use any other language or concepts it will be written explicitly in the directory of the paper), focusing on clarity and educational value.
(This section will be updated as new papers are implemented)
- A Six-Compartment Model for COVID-19 with Transmission Dynamics and Public Health Strategies
- Word2Vec(Efficient Estimation of Word Representations in Vector Space)
- Canonicalizing Open Knowledge Bases
- Orthogonal Nonnegative Matrix Tri-Factorizations for Clustering
- Co-Clustering Triples from Open Information Extraction
- Consolidating Extracted Assertions for Numerical Facts
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Attention Is All You Need
- DICE
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks(RAG)
-
Clone the repository:
git clone https://github.com/aaditya29/Implementing-ML-Papers.git cd Implementing-ML-Papers
Contributions are welcome! If you'd like to add an implementation of a paper or improve an existing one, please follow these steps:
- Fork the repository
- Create a new branch (
git checkout -b feature/new-paper-implementation) - Implement the paper or make your changes
- Add tests for your implementation
- Commit your changes (
git commit -am 'Add implementation of Paper X') - Push to the branch (
git push origin feature/new-paper-implementation) - Create a new Pull Request
Please ensure your code follows the project's coding standards and includes appropriate documentation.