- Getting Started: Get an overview of the course. Import and process data, explore data features, and train and evaluate a classification model.
- Finding Natural Patterns in Data: Use unsupervised learning techniques to group observations based on a set of explanatory variables and discover natural patterns in a data set.
- Classification Methods: Use available classification methods to train data classification models. Make predictions and evaluate the accuracy of a predictive model.
- Improving Predictive Models: Validate model performance. Optimize model properties. Reduce the dimensionality of a data set and simplify machine learning models.
- Regression Methods: Use supervised learning techniques to perform predictive modeling for continuous response variables.
- Conclusion: Learn next steps and give feedback on the course.
Overview
Syllabus
- Course Overview
- Review - Machine Learning Onramp
- Course Example - Grouping Basketball Players
- Low Dimensional Visualization
- k-Means Clustering
- Gaussian Mixture Models
- Interpreting the Clusters
- Hierarchical Clustering
- Project - Clustering
- Course Example - Classifying Fault Types
- Nearest Neighbor Classification
- Classification Trees
- Naive Bayes Classification
- Discriminant Analysis
- Support Vector Machines
- Classification with Neural Networks
- Project - Classification Methods
- Methods for Improving Predictive Models
- Cross Validation
- Reducing Predictors - Feature Transformation
- Reducing Predictors - Feature Selection
- Hyperparameter Optimization
- Ensemble Learning
- Project - Improving Predictive Models
- Course Example - Fuel Economy
- Linear Models
- Stepwise Fitting
- Regularized Linear Models
- SVMs, Trees and Neural Networks
- Gaussian Process Regression
- Project - Regression
- Additional Resources
- Survey
Taught by
Andrea Bayas
