MATLAB File Help: dml.corclas

  corclas template matching correlation based classifier.
 
    DESCRIPTION
    This classifier makes a template for each class by averaging over
    instances of that class. A test sample is classifier as the class which
    corresponds to the template with which the sample has the highest
    correlation.
 
    EXAMPLE
    X = rand(10,20); Y = [1 1 1 1 1 2 2 2 2 2]';
    m = dml.corclas;
    m = m.train(X,Y);
    Z = m.test(X);
 
    REFERENCE
    Distributed and overlapping representations of faces and objects in
    ventral temporal cortex by J. V. Haxby et al.
 
    DEVELOPER
    Ali Bahramisharif (ali@cs.ru.nl)

Superclasses	dml.method
Sealed	false
Construct on load	false

indims	dimensions of the input data (excluding the trial dim and time dim in time series data)
restart	when false, starts at the previously learned parameters; needed for online learning and grid search
template	the template of each class
verbose	whether or not to generate diagnostic output

	model	returns the following parameter:
	test
	train