Repo containing my complete solutions no the Stanford Machine Learning course.
Solutions are written in GNU Octave.
Course can be found on Stanford's Website and hosted on Coursera.
Exercise include:
- Implement linear regression algorithm.
- Build logistic regressor.
- One-vs-all logistic regression for recognising hand-wnitten digits.
- Implementation of backpropogation algorithm and application to hand-written digit recognition.
- Study bias-variance dichotomy with regularized linear regressors.
- Build a spam classifier using SVMs.
- Use K-means clustering to compress an image and PCA to find a low-dimensional representation of face images.
- Implement anomaly-detection algorithm to detect failing servers on a network and use collaborative filtering to build a recommender system for movies.