Statistical Learning for Big Data

Repository for the course "Statistical Learning for Big Data" at Chalmers University of Technology.

Comparing three different classifications methods: KNN, Logistic Regression and LDA. Using k-fold CV and missclassification rate to determine strength.

Project 2 - Clustering

Investigating the impact of linkage (ward and centroid) on hierarchical clustering and covariance type (VEE and EEV) on GMM clustering.

Project 3 - Group Lasso

Exploring group lasso with simulated data. Escpecially looking at how the method handles false/scrambled grouping.

Project 4 - NMF Clustering

Comparing NMF clustering and k-means on a subset of the MNIST fashion dataset.

Exam

Code and answers to the exam.

calvinnsmith/Big-Data

Statistical Learning for Big Data