Parzen Windows
A name for kernel density estimation once common in the pattern recognition community.
A simple classifier into two classes which thresholds a linear combination of the features. Much publicized by F. Rosenblatt around 1960.

Plug-in Classifier
A classifier constructed by assuming that estimated parameter values are in fact the true ones.

  Posterior Probability
The probability of an event conditional on the observations.
  Predictive Classifier
A classifier constructed by averaging over the uncertainty in the estimated parameter values.

  Principal Components
are linear combinations of features with high variance.
  Prior Probability
Probabilities specified before seeing the data, and so based on prior experience or belief. Commonly these are the prior probabilities of the classes.
  Profile Likelihood
Suppose we divide the parameters The profile likelihood for is the likelihood for maximized over .
  Projection Pursuit
methods are based on extracting features (linear combinations of the original features.) Exploratory projection pursuit (Section 9.1) looks for 'interesting' (non-normal) features, and projection pursuit regression uses the extracted features in an additive model.
is the term used for removing parts of trees and networks with the aim of increasing generalization.