Canonical Discriminant Analysis For K Classes
Canonical discriminant analysis finds axes (the number of categories −1 = k − 1 canonical coordinates) that best separate the categories. These linear functions are uncorrelated and define, in effect, an optimal k − 1 space through the n-dimensional cloud of data that best separates (the projections in that space of) the k groups. See "Multiclass LDA" for details below.
Read more about this topic: Linear Discriminant Analysis
Famous quotes containing the words canonical, analysis and/or classes:
“If God bestowed immortality on every man then when he made him, and he made many to whom he never purposed to give his saving grace, what did his Lordship think that God gave any man immortality with purpose only to make him capable of immortal torments? It is a hard saying, and I think cannot piously be believed. I am sure it can never be proved by the canonical Scripture.”
—Thomas Hobbes (1579–1688)
“Cubism had been an analysis of the object and an attempt to put it before us in its totality; both as analysis and as synthesis, it was a criticism of appearance. Surrealism transmuted the object, and suddenly a canvas became an apparition: a new figuration, a real transfiguration.”
—Octavio Paz (b. 1914)
“There are three classes into which all the women past seventy that ever I knew were to be divided: 1. That dear old soul; 2. That old woman; 3. That old witch.”
—Samuel Taylor Coleridge (1772–1834)