https://github.com/kleinyuan/numpy-ml

Implementations of machine learning concepts in modules with basic numpy
https://github.com/kleinyuan/numpy-ml

basics machine-learning numpy

Last synced: 21 days ago
JSON representation

Implementations of machine learning concepts in modules with basic numpy

• Host: GitHub
• URL: https://github.com/kleinyuan/numpy-ml
• Owner: KleinYuan
• License: mit
• Created: 2017-09-17T20:02:36.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-10-31T03:42:56.000Z (over 6 years ago)
• Last Synced: 2024-11-25T18:21:57.773Z (3 months ago)
• Topics: basics, machine-learning, numpy
• Language: Python
• Homepage:
• Size: 5.86 KB
• Stars: 2
• Watchers: 3
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Intro

We implement all machine learning algorithms, concepts and ideas here, with following principles:

- [X] Only use [Numpy](http://www.numpy.org/)

- [X] All in modules/blocks

- [X] No dirty/garbage codes

- [X] As more matrix calculation as possible

- [X] As less for loops as possible

- [X] Write tests

- [X] Self-explained naming convention

# Machine Learning

Technically, we can create a mathematical model for any problems in the world with following elements:

- [X] Problem Definition

- [X] Historical Data

- [X] Model (Hypothesis)

- [X] Error (Loss, cost function, object function)

- [X] Optimizer

# Index

- [X] [Linear Regression](https://github.com/KleinYuan/numpy-ml/blob/master/models/linear_regression.py)

- [X] [Gradient Descent](https://github.com/KleinYuan/numpy-ml/blob/master/optimizers/gradient_descent.py)

# Some Basic Functions

![](http://adilmoujahid.com/images/activation.png)