GDA |
Generalized Discriminant Analysis.
Synopsis:
model = gda(data)
model = gda(data,options)
Description:
This function is implimentation of the Generalized Discriminant
Analysis (GDA) [Baudat01]. The GDA is kernelized version of
the Linear Discriminant Analysis (LDA). It produce the kernel data
projection which increases class separability of the projected
training data.
Input:
data [struct] Labeled training data:
.X [dim x num_data] Training vectors.
.y [1 x num_data] Labels (1,2,..,mclass).
options [struct] Defines kernel and a output dimension:
.ker [string] Kernel identifier (default 'linear');
see 'help kernel' for more info.
.arg [1 x nargs] Kernel arguments (default 1).
.new_dim [1x1] Output dimension (default dim).
Output:
model [struct] Kernel projection:
.Alpha [num_data x new_dim] Multipliers.
.b [new_dim x 1] Bias.
.sv.X [dim x num_data] Training data.
.options [struct] Copy of used options.
.rankK [int] Rank of centered kernel matrix.
.nsv [int] Number of training data.
Example:
in_data = load('iris');
model = gda(in_data,struct('ker','rbf','arg',1));
out_data = kernelproj( in_data, model );
figure; ppatterns( out_data );
See also
KERNELPROJ, KPCA.
About: Statistical Pattern Recognition Toolbox
(C) 1999-2003, Written by Vojtech Franc and Vaclav Hlavac
Czech Technical University Prague
Faculty of Electrical Engineering
Center for Machine Perception
Modifications:
24-may-2004, VF
4-may-2004, VF