https://github.com/jnlandu/base_ml_algo

Implementation of the Basic Machine Learning Algorithms
https://github.com/jnlandu/base_ml_algo

Last synced: about 1 month ago
JSON representation

Implementation of the Basic Machine Learning Algorithms

• Host: GitHub
• URL: https://github.com/jnlandu/base_ml_algo
• Owner: jnlandu
• Created: 2024-03-12T17:50:54.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-03-27T02:09:36.000Z (9 months ago)
• Last Synced: 2024-03-27T03:24:43.542Z (9 months ago)
• Language: Python
• Size: 26.4 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# base_ml_algo: 

Developing version of the implementation of basic machine learning algorithms taught/discussed in class at the AIMS AMMI program (visit https://aimsammi.org/)

### Short details

This repository contains assignmemts, tests, quizes, and projects, that we did/will be doing at  the AIMS AMMI program. For the actual version, no much is done althought some a few works are already uploaded, notaby the implementation:

* gradient descent method and its variants: Mini-Bacth GD  and Stochastic GD.

* logistic regression, implementaion from scratch. The details about the dataset used will be given later.

* linear regression, likewise, details for the the datasets will be discussed later.

Most of those codes are written in python and use several packages libraies such as `numpy`, `pandas`,`pytorch`, etc.

### Changes from now to March 31, 2024

We aim at to:

* improve the code just uploaded, broaden it and include more features that have not appeared so far.

* improve also the readability of the codes.

* add related (short courses/short summary) of each concepts and/or techniques that have been used so far.

* have the same codes but written in `R` (or `Julia`).

* add collaboration, where needed.

### Datasets

For  most of the present codes, we use the dataset provided by an appropriate library/package. For instance for the logistic implementation, the wide-known dataset `iris` from  `sklearn` was used to test our codes.