This talk will describe the differences between supervised and unsupervised techniques and the pros and cons of each. It will explain a couple of document classification techniques, such as SVM, decision tree/forest, and a couple of clustering techniques, such as graph-based ones and Latent Dirichlet Allocation which is a probabilistic graphical model.
We will ask how you evaluate how well your algorithm is doing, and reinforce what kind of problems require which solution and when is it advantageous to combine the two.
You can view Chris’ presentation below:
