cassiesu / data_mining_exercise

Exercises in data mining course at ETHz (Fall 2015)

data_mining_exercise

Exercises in data mining course at ETHz (Fall 2015) Implemented several machine learning algorithms in the framework of Hadoop MapReduce to deal with real-world large scale dataset.

Algorithms included:

detecting video samples using Locality Sensitive Hashing;

classifying images using online SVM;

extract representative elements of image by Kmeans with coresets;

learning recommender systems using enhanced UCB.