Andrew H. Fagg (andrewhfagg@gmail.com)
Example code, code skeletons and assignments for the Machine Learning Practice course
Topics include:
- Representing information and preparing data for use with ML methods
- Classifiers and feature importance, including K-nearest neighbors, logistic regression, support vector machines
- Decision trees: ensemble methods, random forests, and boosting
- Regression and combating over-fitting: ridge regression, lasso, elastic nets, polynomial regression, support vector regression
- Nonlinear dimensionality reduction: kernel PCA, local linear embedding, ISOmap, multidimensional scaling
- Semi-supervised learning: label spreading, label propagation
- Unsupervised learning
- Evaluation in ML: metrics, cross-validation, statistics, addressing the multiple comparisons problem
- Programming skills in an object-oriented language.
- Python
- Pandas
- Numpy
- Scikit-Learn