Unfoldm: Difference between revisions
Jump to navigation
Jump to search
imported>Jeremy (Importing text file) |
imported>Jeremy No edit summary |
||
| Line 1: | Line 1: | ||
===Purpose=== | ===Purpose=== | ||
| Line 10: | Line 9: | ||
===Description=== | ===Description=== | ||
UNFOLDM unfolds the input matrix xaug to create a matrix of unfolded row vectors xmpca for MPCA. xaug contains nsamp matrices '''A'''j augmented such that [xaug] = [A1; A2; ...; Ansamp]. For example, for xaug of size (nsamp\*m by n) each matrix '''A'''j is of size m by n. For '''A'''j each m by 1 column ai is transposed and augmented such that [bj] = [a1', a2', ..., an'] and [xmpca] = [b1; b2; ...; bnsamp]. Note: the '''A'''j should all be the same size. | UNFOLDM unfolds the input matrix <tt>xaug</tt> to create a matrix of unfolded row vectors xmpca for MPCA. <tt>xaug</tt> contains <tt>nsamp</tt> matrices '''A'''j augmented such that <tt>[xaug] = [A1; A2; ...; Ansamp]</tt>. For example, for <tt>xaug</tt> of size (<tt>nsamp\*m by n</tt>) each matrix '''A'''j is of size m by n. For '''A'''j each m by 1 column <tt>ai</tt> is transposed and augmented such that <tt>[bj] = [a1', a2', ..., an']</tt> and <tt>[xmpca] = [b1; b2; ...; bnsamp]</tt>. Note: the '''A'''j should all be the same size. | ||
===Examples=== | ===Examples=== | ||
<pre> | |||
a = [1 2 3 | a = [1 2 3 | ||
4 5 6 | |||
-1 -2 -3 | |||
-4 -5 -6] | |||
xmpca = unfoldm(a,2) | xmpca = unfoldm(a,2) | ||
xmpca = [1 4 2 5 3 6 | xmpca = [1 4 2 5 3 6 | ||
-1 -4 -2 -5 -3 -6] | -1 -4 -2 -5 -3 -6] | ||
</pre> | |||
===See Also=== | ===See Also=== | ||
[[gscale]], [[mpca]], [[pca]], [[reshape]] | [[gscale]], [[mpca]], [[pca]], [[reshape]] | ||
Revision as of 10:19, 10 October 2008
Purpose
Unfolds an augmented matrix for MPCA.
Synopsis
- xmpca = unfoldm(xaug,nsamp)
Description
UNFOLDM unfolds the input matrix xaug to create a matrix of unfolded row vectors xmpca for MPCA. xaug contains nsamp matrices Aj augmented such that [xaug] = [A1; A2; ...; Ansamp]. For example, for xaug of size (nsamp\*m by n) each matrix Aj is of size m by n. For Aj each m by 1 column ai is transposed and augmented such that [bj] = [a1', a2', ..., an'] and [xmpca] = [b1; b2; ...; bnsamp]. Note: the Aj should all be the same size.
Examples
a = [1 2 3
4 5 6
-1 -2 -3
-4 -5 -6]
xmpca = unfoldm(a,2)
xmpca = [1 4 2 5 3 6
-1 -4 -2 -5 -3 -6]