Data Science III (course at WHZ)
Contents
Data Science III (course at WHZ)#
Part three of the data science lecture series continues discussion of supervised machine learning. Further methods like decision trees and support vector machines are introduced. Then we move on to unsupervised machine learning covering clustering methods and techniques for dimensionality reduction.
Supervised Learning#
Week 1 (Decision Trees)#
Self-study
IBAN recognition (project)
Practice session
-
Decision Tree (project)
Week 2 (Ensemble Methods)#
Lectures
Self-study
revisit Worked Example: House Prices II
Practice session
-
Random Forest (project)
-
A Random Forest for House Prices (project)
Week 3 (Support-Vector Machines)#
Week 4 (Naive Bayes)#
Lectures
Naive Bayes Classification (without kernel density estimates)
Self-study
Naive Bayes Classification (kernel density estimates, bonus)
Practice session
-
Naive Bayes Classification (project)
Week 5 (Text Classification)#
Week 6 (Text Classification)#
Lectures
Self-study
Practice session
-
Blog Author Classification (Training) (project)
Blog Author Classification (Test) (project)
Unsupervised Learning#
Week 7 (Introduction, Centroid-based Clustering)#
Self-study
Practice session
Week 8 (Hierarchical Clustering)#
Lectures
Self-study
Practice session
Supermarket Customers (project)
-
Hierarchical Clustering (project)
Week 9 (Density-based Distribution-based Clustering)#
Self-study
Practice session
Week 10 (Autoencoders)#
Lectures
Self-study
Practice session
Week 11 (Nonlinear Dimensionality Reduction, Kernel PCA)#
Self-study
Feature Reduction (reread PCA section)
Practice session
Week 12 (Multidimensional Scaling)#
Lectures
Self-study
Feature Reduction (reread PCA section)
Practice session
Color Perception (project)
Forest Fires (project)
Week 13 (LLE, SNE, SOM)#
Self-study
Practice session
-
t-SNE for QMNIST (project)
-
House Prices SOM (project)