Lecture 5 – February 17 , 2016

This lecture is on dimensionality reduction, which aims at ‘squashing’ down the dimensionality while still preserving some geometric properties. The motivation behind this technique is that many types of data are high-dimensional, and it will be operationally much easier to manipulate these data in a lower dimension. For instance, the bag-of-words representation of documents, which treats every document as a vector of word counts, can easily have tens of thousands of dimensions. In domains where images or videos are the subjects of interest, the dimension is even greater.