|
makeGramMatrix
|
The makeGramMatrix function returns the N by N matrix containing the
dot products of the row vectors in the input {NumMatrix}, known as the
Gram matrix. The makeGramMatrix function will only receive a number matrix
and always returns a new number Matrix containing the result. The input argument {NumMatrix} must be an N by M number matrix representing the
original independent variable observations (the dependent variable is omitted) in the
form of: The output argument will be an N by N number matrix containing the dot products of the
row vectors of the original observation matrix X, where:
G[r,c] = vectorDotProduct(rowX[r],rowX[c]). If the optional dependent variable number vector is included, The output argument will
be an N by N+1 number matrix containing the dot products of the row vectors of the
original observation matrix X, where:
G[r,c] = vectorDotProduct(rowX[r],rowX[c]), plus the N+1th column will contain
the original dependent values. When to use The makeGramMatrix functionis a non-destructive function useful when you want
to create a Gram matrix in preparation for dual form regression. See Cristianini,
"Support Vector Machines", page 169.
x x x x... y
x x x x... y
....
x x x x... y
(makeGramMatrix NumMatrix) A new number Matrix object containing the dot products of the row vectors of the
original observation matrix.
Here are a number of links to Lambda coding examples which contain this instruction in various use cases.
Example_NumMatrix_makeGramMatrix_001
Here are the links to the data types of the function arguments. Here are also a number of links to functions having arguments with any of these data types.
You can always talk with the AIS at aiserver.sourceforge.net.
Name
Description
AIS Types NumMatrix Matrix containing the original independent observations NumMatrix
Returns:
Examples
Argument Types
NumMatrix
Vector
How do I contact the AIS team?