https://github.com/supreme-gg-gg/python-ml-course
Coding notes from Andrew Ng's machine learning course, reference for other fellow students
https://github.com/supreme-gg-gg/python-ml-course
artificial-intelligence machine-learning machine-learning-algorithms neural-network python reinforcement-learning supervised-learning tensorflow unsupervised-learning
Last synced: 4 months ago
JSON representation
Coding notes from Andrew Ng's machine learning course, reference for other fellow students
- Host: GitHub
- URL: https://github.com/supreme-gg-gg/python-ml-course
- Owner: supreme-gg-gg
- Created: 2024-08-09T02:07:14.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-05-08T00:48:09.000Z (about 1 year ago)
- Last Synced: 2025-06-07T11:07:46.112Z (about 1 year ago)
- Topics: artificial-intelligence, machine-learning, machine-learning-algorithms, neural-network, python, reinforcement-learning, supervised-learning, tensorflow, unsupervised-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 7.83 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Machine Learning Notes
## Abstract
This is my personal coding notes from the Machine Learning Specialization (3 courses in total) I took during my free time on Coursera. [You can access the course by Andrew Ng here](https://www.coursera.org/specializations/machine-learning-introduction) and audit it for free. They are some great learning resources and took just around one month for normal speed.
It built some foundation for my other AI project in quantitative finance (which I will link below once finished). These codes are not meant to be used for academic or commercial purposes but purely for individual learning.
## Table of Content
Here's a summary that you might or might not find useful:
| Course | Topic | Files |
| --- | --- | --- |
| Supervised learning | Linear regression | linear.py, regularisation.py, restaurant.py |
| | Logistic regression | logarithmic.py, sklearn-regression.py, microchip.py |
| Deep Learning | Neural Networks | coffee-numpy.py, multiclass.py, coffee-tf.py |
| | Evaluate models | optimize-neural.ipynb, digits.ipynb, digits2.ipynb |
| | Decision trees | trees.ipynb |
| Unsupervised/Reinforcement | Unsupervised | anomaly.ipynb, clustering.ipynb |
| | Reinforcement | policy.py, lunar-rover.ipynb |
_Honestly, the organisation is pretty chaotic..._
## How to use
* If you want to see some of these for inspiration or other purposes, set up the environment using `conda create --name --file requirements.txt`.
* If you are not using conda set up a venv and install the libraries using `pip install --upgrade numpy matplotlib tensorflow keras gym scikit-learn`.
* Feel free to explore around and run the codes. You can copy any part of this repo for your own use.
* **These codes are not meant for production or distribution, so there is absolutely no rigorous testing and quality verification process.** I will not be responsible for maintaining the contents of this repo.
* The data files are attached and connected already
***
_Finally, I wish you good luck in learning AI and ML!_ I really found this to be an intriguing field of study especially when you get to witness everything underneath the hood of all its cool applications!