Machine Learning excercises from the Coursera Machine Learning course from Stanford University.
All of the excercises are actually part of the assignments that you get during the course. Before diving in, if you are following the course, try to write your own implementation before you see how it has been implemented here.
The contents of this repo by topic:
- Linear Regression
- Logistic Regression
- Multiclass Classification & Neural Networks: Classification
- Neural Networks: Learning
- Neural Networks: Regularization, Bias vs. Variance
- SVM
- Unsupervised Learning & Dimensionality Reduction
- Anomaly Detection & Recommender Systems
All the exercises are written in Octave, a free alternative to Matlab. Check out the install instructions:
It's to be noted that parts of the implementations have been borrowed from Swizec Teller.
More learning material can be found at:
- CS229 Stanford Course
- Awesome Machine Learning
Some good books/papers:
- Machine Learning for Hackers
- Programming Collective Intelligence: Building Smart Web 2.0 Applications
- A Brief Introduction into Machine Learning
- Linear Algebra Review
And some good YouTube videos:
