reference
Mathematical principles of PCA
[Rpm] of Matlab seeking variance, mean, standard deviation, covariance function
Principal component analysis (PCA) Detailed principles
PCA algorithm
Significance is two matrix multiplication of each column to the right column vector matrix transformation matrix to the left of each vector is trekking space group represented go . More abstract that a linear transformation matrix may represent one.
Above we discussed the selection of different groups can be given different representations of the same set of data, and if the number of groups is less than the dimension of the vector itself, the effect of dimension reduction can be achieved.
A set of N -dimensional vector reduced K dimensions ( K greater than 0 and less than N ), the goal is to select K units (modulo 1 ) After an orthogonal basis, such that the original data is converted to the set of groups, each field twenty-two covariance between 0 , and the variance of the field is as large as possible (in the perpendicular constraint, taking the maximum of K number variance) .
Eigenvalues and directions: feature vector representing the direction of stretching, the feature value representing the degree of stretching.
