fa13-cs188-lecture-22-1PP

One opon small squared euclidean distance kmeans

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ome kernels not as usefully thought of in their expanded representa)on, e.g. RBF kernels   Kernels let us compute with these features implicitly   Example: implicit dot product in quadra)c kernel takes much less space and )me per dot product   Of course, there’s the cost for using the pure dual algorithms: you need to compute the similarity to every training datum Recap: Classifica)on   Classifica)on systems:   Supervised learning   Make a predic)on given evidence   We’ve seen several methods for this   Useful when you have labeled data Clustering   Clustering systems:   Unsupervised learning   Detect paOerns in unlabeled data   E.g. group emails or search results   E.g. find categories of customers   E.g. detect anomalous program execu)ons   Useful when don’t know what you’re looking for   Requires data, but no labels   OYen get gibberish Clustering C...
View Full Document

Ask a homework question - tutors are online