Part IV Generative Learning algorithms

CS229 Lecture notesAndrew NgPart IVGenerative Learning algorithmsSo far, we ve mainly been talking about Learning algorithms that modelp(y|x; ), the conditional distribution ofygivenx. For instance, logisticregression modeledp(y|x; ) ash (x) =g( Tx) wheregis the sigmoid func-tion. In these notes, we ll talk about a different type of Learning a classification problem in which we want to learn to distinguishbetween elephants (y= 1) and dogs (y= 0), based on some features ofan animal. Given a training set, an algorithm like logistic regression orthe perceptron algorithm (basically) tries to find a straight line that is, adecision boundary that separates the elephants and dogs. Then, to classifya new animal as either an elephant or a dog, it checks on which side of thedecision boundary it falls, and makes its prediction s a different approach. First, looking at elephants, we can buildamodel of what elephants look like. Then, looking at dogs, we can build aseparate model of what dogs look like.

5 1.2 The Gaussian Discriminant Analysis model When we have a classification problem in which the input features x are continuous-valued random variables, we can then use the Gaussian Discrim-

Loading..

Tags:

  Analysis, Generative

Information

Related search queries