Implementations of machine learning algorithm by Python 3
The folders included demo programs for leverage scikit-learn library to solve tasks with Python 3.
| Algorithm | Description | Link |
|---|---|---|
| Linear regression | Linear regression is a linear modeling to describe the relation between a scalar dependent variable y and one or more independent variables, X. | Source Code |
| Logistic regression | logit regression. It is different to regression analysis. A linear probability classifier model to categorize random variable Y being 0 or 1 by given experiment data. Assumes each of categorize are independent and irrelevant alternatives. The model p(y=1|x, b, w) = sigmoid(g(x)) where g(x)=b+wTx. The sigmoid function = 1/1+e^(-a) where a = g(x). | Source Code |
| Gaussian Mixture Models (GMMs) | GMMs are among the most statistically mature methods for data clustering (and density estimation). It assumes each component generates data from a Gaussian distribution. | Source Code |
| K-Means | One of most famous and easy to understand clustering algorithm | Source Code |
| PLA | Perceptron Learning Algorithm. A solver for binary classification task. | Source Code |
- Machine learning-CSCI567 by Prof. Fei Sha at University of Southern California, Fall 2017.
- scikit-learn: http://scikit-learn.org/stable/
- Gaussian Mixture Models - Tutorial Slides by Andrew Moore : http://www.cs.cmu.edu/~./awm/tutorials/gmm.html
- logistic regression: https://en.wikipedia.org/wiki/Logistic_regression
Cheng-Lin Li@University of Southern California [email protected] or [email protected]