Understanding L2-norm in MATLAB - matlab

I have two matrices, x and y, which are the same size. They are two estimations of the same data field. I want to quantify the difference between them across the whole matrix. Is norm(x-y,2) how this is normally done? What units is this in - if x and y are velocities in mm/sec, and I want to turn the L2-norm into a percentage of some reference velocity, does that make any sense?
Should this belong in Math?

Norm 2 of a matrix in Matlab is equal to root square of sum of squares of all elements. The all norm functions do not change units( its because you apply both square and root-square).
If you want compare the result with a reference velocity, it is better to use other measures like RMS (Root Mean Square). It is similar to norm but you should normalize the sum of squares before applying the root square. (this measure also does not change units)
The RMS of this matrix can be interpreted as :
How much velocity is changed at each place (x and y) in average.(the unit is mm/sec)

I'm not sure what you mean by "quantify the difference", so this is what I do know...
norm(x) == norm(x, 2)
Equivalent since L2 norm is default. From matlab help
n = norm(X) returns the 2-norm or maximum singular value of matrix X.
So, if the max singular value of the difference of your two matrices is what you want, then you have the right function.

norm(X,2) or just norm(X) will give you the l2 norm or the euclidian norm of X. X can be a matrix or a Vector. Be it a vector or a matrix, norm will be calculated by first squaring all elements, then summing them up and taking a square root yielding a single value as the answer. What you are trying to do will in some sense give you the magnitude of the difference between the two matrices. The units will be same as that of matrix elements.

Related

Finding length between a lot of elements

I have an image of a cytoskeleton. There are a lot of small objects inside and I want to calculate the length between all of them in every axis and to get a matrix with all this data. I am trying to do this in matlab.
My final aim is to figure out if there is any axis with a constant distance between the object.
I've tried bwdist and to use connected components without any luck.
Do you have any other ideas?
So, the end goal is that you want to globally stretch this image in a certain direction (linearly) so that the distances between nearest pairs end up the closest together, hopefully the same? Or may you do more complex stretching ? (note that with arbitrarily complex one you can always make it work :) )
If linear global one, distance in x' and y' is going to be a simple multiplication of the old distance in x and y, applied to every pair of points. So, the final euclidean distance will end up being sqrt((SX*x)^2 + (SY*y)^2), with SX being stretch in x and SY stretch in y; X and Y are distances in X and Y between pairs of points.
If you are interested in just "the same" part, solution is not so difficult:
Find all objects of interest and put their X and Y coordinates in a N*2 matrix.
Calculate distances between all pairs of objects in X and Y. You will end up with 2 matrices sized N*N (with 0 on the diagonal, symmetric and real, not sure what is the name for that type of matrix).
Find minimum distance (say this is between A an B).
You probably already have this. Now:
Take C. Make N-1 transformations, which all end up in C->nearestToC = A->B. It is a simple system of equations, you have X1^2*SX^2+Y1^2*SY^2 = X2^2*SX^2+Y2*SY^2.
So, first say A->B = C->A, then A->B = C->B, then A->B = C->D etc etc. Make sure transformation is normalized => SX^2 + SY^2 = 1. If it cannot be found, the only valid transformation is SX = SY = 0 which means you don't have solution here. Obviously, SX and SY need to be real.
Note that this solution is unique except in case where X1 = X2 and Y1 = Y2. In this case, grab some other point than C to find this transformation.
For each transformation check the remaining points and find all nearest neighbours of them. If distance is always the same as these 2 (to a given tolerance), great, you found your transformation. If not, this transformation does not work and you should continue with the next one.
If you want a transformation that minimizes variations between distances (but doesn't require them to be nearly equal), I would do some optimization method and search for a minimum - I don't know how to find an exact solution otherwise. I would pick this also in case you don't have linear or global stretch.
If i understand your question correctly, the first step is to obtain all of the objects center of mass points in the image as (x,y) coordinates. Then, you can easily compute all of the distances between all points. I suggest taking a look on a histogram of those distances which may provide some information as to the nature of distance distribution (for example if it is uniformly random, or are there any patterns that appear).
Obtaining the center of mass points is not an easy task, consider transforming the image into a binary one, or some sort of background subtraction with blob detection or/and edge detector.
For building a histogram you can use histogram.

Computing the SVD of a rectangular matrix

I have a matrix like M = K x N ,where k is 49152 and is the dimension of the problem and N is 52 and is the number of observations.
I have tried to use [U,S,V]=SVD(M) but doing this I get less memory space.
I found another code which uses [U,S,V]=SVD(COV(M)) and it works well. My questions are what is the meaning of using the COV(M) command inside the SVD and what is the meaning of the resultant [U,S,V]?
Finding the SVD of the covariance matrix is a method to perform Principal Components Analysis or PCA for short. I won't get into the mathematical details here, but PCA performs what is known as dimensionality reduction. If you like a more formal treatise on the subject, you can read up on my post about it here: What does selecting the largest eigenvalues and eigenvectors in the covariance matrix mean in data analysis?. However, simply put dimensionality reduction projects your data stored in the matrix M onto a lower dimensional surface with the least amount of projection error. In this matrix, we are assuming that each column is a feature or a dimension and each row is a data point. I suspect the reason why you are getting more memory occupied by applying the SVD on the actual data matrix M itself rather than the covariance matrix is because you have a significant amount of data points with a small amount of features. The covariance matrix finds the covariance between pairs of features. If M is a m x n matrix where m is the total number of data points and n is the total number of features, doing cov(M) would actually give you a n x n matrix, so you are applying SVD on a small amount of memory in comparison to M.
As for the meaning of U, S and V, for dimensionality reduction specifically, the columns of V are what are known as the principal components. The ordering of V is in such a way where the first column is the first axis of your data that describes the greatest amount of variability possible. As you start going to the second columns up to the nth column, you start to introduce more axes in your data and the variability starts to decrease. Eventually when you hit the nth column, you are essentially describing your data in its entirety without reducing any dimensions. The diagonal values of S denote what is called the variance explained which respect the same ordering as V. As you progress through the singular values, they tell you how much of the variability in your data is described by each corresponding principal component.
To perform the dimensionality reduction, you can either take U and multiply by S or take your data that is mean subtracted and multiply by V. In other words, supposing X is the matrix M where each column has its mean computed and the is subtracted from each column of M, the following relationship holds:
US = XV
To actually perform the final dimensionality reduction, you take either US or XV and retain the first k columns where k is the total amount of dimensions you want to retain. The value of k depends on your application, but many people choose k to be the total number of principal components that explains a certain percentage of your variability in your data.
For more information about the link between SVD and PCA, please see this post on Cross Validated: https://stats.stackexchange.com/q/134282/86678
Instead of [U, S, V] = svd(M), which tries to build a matrix U that is 49152 by 49152 (= 18 GB 😱!), do svd(M, 'econ'). That returns the “economy-class” SVD, where U will be 52 by 52, S is 52 by 52, and V is also 52 by 52.
cov(M) will remove each dimension’s mean and evaluate the inner product, giving you a 52 by 52 covariance matrix. You can implement your own version of cov, called mycov, as
function [C] = mycov(M)
M = bsxfun(#minus, M, mean(M, 1)); % subtract each dimension’s mean over all observations
C = M' * M / size(M, 1);
(You can verify this works by looking at mycov(randn(49152, 52)), which should be close to eye(52), since each element of that array is IID-Gaussian.)
There’s a lot of magical linear algebraic properties and relationships between the SVD and EVD (i.e., singular value vs eigenvalue decompositions): because the covariance matrix cov(M) is a Hermitian matrix, it’s left- and right-singular vectors are the same, and in fact also cov(M)’s eigenvectors. Furthermore, cov(M)’s singular values are also its eigenvalues: so svd(cov(M)) is just an expensive way to get eig(cov(M)) 😂, up to ±1 and reordering.
As #rayryeng explains at length, usually people look at svd(M, 'econ') because they want eig(cov(M)) without needing to evaluate cov(M), because you never want to compute cov(M): it’s numerically unstable. I recently wrote an answer that showed, in Python, how to compute eig(cov(M)) using svd(M2, 'econ'), where M2 is the 0-mean version of M, used in the practical application of color-to-grayscale mapping, which might help you get more context.

Rotate a basis to align to vector

I have a matrix M of size NxP. Every P columns are orthogonal (M is a basis). I also have a vector V of size N.
My objective is to transform the first vector of M into V and to update the others in order to conservate their orthogonality. I know that the origins of V and M are the same, so it is basically a rotation from a certain angle. I assume we can find a matrix T such that T*M = M'. However, I can't figure out the details of how to do it (with MATLAB).
Also, I know there might be an infinite number of transforms doing that, but I'd like to get the simplest one (in which others vectors of M approximately remain the same, i.e no rotation around the first vector).
A small picture to illustrate. In my actual case, N and P can be large integers (not necessarily 3):
Thanks in advance for your help!
[EDIT] Alternative solution to Gram-Schmidt (accepted answer)
I managed to get a correct solution by retrieving a rotation matrix R by solving an optimization problem minimizing the 2-norm between M and R*M, under the constraints:
V is orthogonal to R*M[1] ... R*M[P-1] (i.e V'*(R*M[i]) = 0)
R*M[0] = V
Due to the solver constraints, I couldn't indicate that R*M[0] ... R*M[P-1] are all pairwise orthogonal (i.e (R*M)' * (R*M) = I).
Luckily, it seems that with this problem and with my solver (CVX using SDPT3), the resulting R*M[0] ... R*M[P-1] are also pairwise orthogonal.
I believe you want to use the Gram-Schmidt process here, which finds an orthogonal basis for a set of vectors. If V is not orthogonal to M[0], you can simply change M[0] to V and run Gram-Schmidt, to arrive at an orthogonal basis. If it is orthogonal to M[0], instead change another, non-orthogonal vector such as M[1] to V and swap the columns to make it first.
Mind you, the vector V needs to be in the column space of M, or you will always have a different basis than you had before.
Matlab doesn't have a built-in Gram-Schmidt command, although you can use the qr command to get an orthogonal basis. However, this won't work if you need V to be one of the vectors.
Option # 1 : if you have some vector and after some changes you want to rotate matrix to restore its orthogonality then, I believe, this method should work for you in Matlab
http://www.mathworks.com/help/symbolic/mupad_ref/numeric-rotationmatrix.html
(edit by another user: above link is broken, possible redirect: Matrix Rotations and Transformations)
If it does not, then ...
Option # 2 : I did not do this in Matlab but a part of another task was to find Eigenvalues and Eigenvectors of the matrix. To achieve this I used SVD. Part of SVD algorithm was Jacobi Rotation. It says to rotate the matrix until it is almost diagonalizable with some precision and invertible.
https://math.stackexchange.com/questions/222171/what-is-the-difference-between-diagonalization-and-orthogonal-diagonalization
Approximate algorithm of Jacobi rotation in your case should be similar to this one. I may be wrong at some point so you will need to double check this in relevant docs :
1) change values in existing vector
2) compute angle between actual and new vector
3) create rotation matrix and ...
put Cosine(angle) to diagonal of rotation matrix
put Sin(angle) to the top left corner of the matric
put minus -Sin(angle) to the right bottom corner of the matrix
4) multiple vector or matrix of vectors by rotation matrix in a loop until your vector matrix is invertible and diagonalizable, ability to invert can be calculated by determinant (check for singularity) and orthogonality (matrix is diagonalized) can be tested with this check - if Max value in LU matrix is less then some constant then stop rotation, at this point new matrix should contain only orthogonal vectors.
Unfortunately, I am not able to find exact pseudo code that I was referring to in the past but these links may help you to understand Jacobi Rotation :
http://www.physik.uni-freiburg.de/~severin/fulltext.pdf
http://web.stanford.edu/class/cme335/lecture7.pdf
https://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2003/rapporter03/maleko_mercy_03003.pdf

it is possible determinant of matrix(256*256) be infinite

i have (256*1) vectors of feature come from (16*16) of gray images. number of vectors is 550
when i compute Sample covariance of this vectors and compute covariance matrix determinant
answer is inf
it is possible determinant of finite matrix with finite range (0:255) value be infinite or i mistake some where?
in fact i want classification with bayesian estimation , my distribution is gaussian and when
i compute determinant be inf and ultimate Answer(likelihood) is zero .
some part of my code:
Mean = mean(dataSet,2);
MeanMatrix = Mean*ones(1,NoC);
Xc = double(dataSet)-MeanMatrix; % transform data to the origine
Sigma = (1/NoC) *Xc*Xc'; % calculate sample covariance matrix
Parameters(i).M = Mean';
Parameters(i).C = Sigma;
likelihoods(i) = (1/(2*pi*sqrt(det(params(i).C)))) * (exp(-0.5 * (double(X)-params(i).M)' * inv(params(i).C) * (double(X)-params(i).M)));
variable i show my classes;
variable X show my feature vector;
Can the determinant of such matrix be infinite? No it cannot.
Can it evaluate as infinite? Yes definitely.
Here is an example of a matrix with a finite amount of elements, that are not too big, yet the determinant will rarely evaluate as a finite number:
det(rand(255)*255)
In your case, probably what is happening is that you have too few datapoints to produce a full-rank covariance matrix.
For instance, if you have N examples, each with dimension d, and N<d, then your d x d covariance matrix will not be full rank and will have a determinant of zero.
In this case, a matrix inverse (precision matrix) does not exist. However, attempting to compute the determinant of the inverse (by taking 1/|X'*X|=1/0 -> \infty) will produce an infinite value.
One way to get around this problem is to set the covariance to X'*X+eps*eye(d), where eps is a small value. This technique corresponds to placing a weak prior distribution on elements of X.
no it is not possible. it may be singular but taking elements a large value has will have a determinant value.

Mahalanobis distance in matlab: pdist2() vs. mahal() function

I have two matrices X and Y. Both represent a number of positions in 3D-space. X is a 50*3 matrix, Y is a 60*3 matrix.
My question: why does applying the mean-function over the output of pdist2() in combination with 'Mahalanobis' not give the result obtained with mahal()?
More details on what I'm trying to do below, as well as the code I used to test this.
Let's suppose the 60 observations in matrix Y are obtained after an experimental manipulation of some kind. I'm trying to assess whether this manipulation had a significant effect on the positions observed in Y. Therefore, I used pdist2(X,X,'Mahalanobis') to compare X to X to obtain a baseline, and later, X to Y (with X the reference matrix: pdist2(X,Y,'Mahalanobis')), and I plotted both distributions to have a look at the overlap.
Subsequently, I calculated the mean Mahalanobis distance for both distributions and the 95% CI and did a t-test and Kolmogorov-Smirnoff test to asses if the difference between the distributions was significant. This seemed very intuitive to me, however, when testing with mahal(), I get different values, although the reference matrix is the same. I don't get what the difference between both ways of calculating mahalanobis distance is exactly.
Comment that is too long #3lectrologos:
You mean this: d(I) = (Y(I,:)-mu)inv(SIGMA)(Y(I,:)-mu)'? This is just the formula for calculating mahalanobis, so should be the same for pdist2() and mahal() functions. I think mu is a scalar and SIGMA is a matrix based on the reference distribution as a whole in both pdist2() and mahal(). Only in mahal you are comparing each point of your sample set to the points of the reference distribution, while in pdist2 you are making pairwise comparisons based on a reference distribution. Actually, with my purpose in my mind, I think I should go for mahal() instead of pdist2(). I can interpret a pairwise distance based on a reference distribution, but I don't think it's what I need here.
% test pdist2 vs. mahal in matlab
% the purpose of this script is to see whether the average over the rows of E equals the values in d...
% data
X = []; % 50*3 matrix, data omitted
Y = []; % 60*3 matrix, data omitted
% calculations
S = nancov(X);
% mahal()
d = mahal(Y,X); % gives an 60*1 matrix with a value for each Cartesian element in Y (second matrix is always the reference matrix)
% pairwise mahalanobis distance with pdist2()
E = pdist2(X,Y,'mahalanobis',S); % outputs an 50*60 matrix with each ij-th element the pairwise distance between element X(i,:) and Y(j,:) based on the covariance matrix of X: nancov(X)
%{
so this is harder to interpret than mahal(), as elements of Y are not just compared to the "mahalanobis-centroid" based on X,
% but to each individual element of X
% so the purpose of this script is to see whether the average over the rows of E equals the values in d...
%}
F = mean(E); % now I averaged over the rows, which means, over all values of X, the reference matrix
mean(d)
mean(E(:)) % not equal to mean(d)
d-F' % not zero
% plot output
figure(1)
plot(d,'bo'), hold on
plot(mean(E),'ro')
legend('mahal()','avaraged over all x values pdist2()')
ylabel('Mahalanobis distance')
figure(2)
plot(d,'bo'), hold on
plot(E','ro')
plot(d,'bo','MarkerFaceColor','b')
xlabel('values in matrix Y (Yi) ... or ... pairwise comparison Yi. (Yi vs. all Xi values)')
ylabel('Mahalanobis distance')
legend('mahal()','pdist2()')
One immediate difference between the two is that mahal subtracts the sample mean of X from each point in Y before computing distances.
Try something like E = pdist2(X,Y-mean(X),'mahalanobis',S); to see if that gives you the same results as mahal.
Note that
mahal(X,Y)
is equivalent to
pdist2(X,mean(Y),'mahalanobis',cov(Y)).^2
Well, I guess there are two different ways to calculate mahalanobis distance between two clusters of data like you explain above:
1) you compare each data point from your sample set to mu and sigma matrices calculated from your reference distribution (although labeling one cluster sample set and the other reference distribution may be arbitrary), thereby calculating the distance from each point to this so called mahalanobis-centroid of the reference distribution.
2) you compare each datapoint from matrix Y to each datapoint of matrix X, with, X the reference distribution (mu and sigma are calculated from X only)
The values of the distances will be different, but I guess the ordinal order of dissimilarity between clusters is preserved when using either method 1 or 2? I actually wonder when comparing 10 different clusters to a reference matrix X, or to each other, if the order of the dissimilarities would differ using method 1 or method 2? Also, I can't imagine a situation where one method would be wrong and the other method not. Although method 1 seems more intuitive in some situations, like mine.