Problem reconstructing retained principal components
PCA is applied to centered data. Observe that |mean(score)| is close to a vector of zeros. Rotating the scores back to the origi...

9 years ago | 0

| accepted

Linear Discriminant analysis WITH variable selection
Here is an example in the doc: <http://www.mathworks.com/help/stats/discriminant-analysis.html#btaf5dv> It shows how to use the ...

9 years ago | 0

Leave-One-Out with ROC
Here is an example for cross-validating a discriminant model: <http://www.mathworks.com/help/stats/discriminant-analysis.html#bs...

9 years ago | 0

| accepted

SVM - SVMTRAIN method SMO (error: No convergence achieved within maximum number of iterations)
You can increase the maximal number of iterations. See 'options' in the doc or help for |svmtrain|.

9 years ago | 0

Perfcurve with multiple negative classes
By default, the Y criterion is TPR computed for all possible score thresholds. The score thresholds are distinct values in the 2...

9 years ago | 0

| accepted

What decision tree learning algorithm does MATLAB use to create decision trees?
|classregtree| uses the CART algorithm described in the Classification and Regression Trees book by Breiman et al.

9 years ago | 0

| accepted

How to use option "stream" of Kmeans
Does this help? help parallelstats

9 years ago | 0

| accepted

How to build a correct spline kernel for svm
Check out this thread and let us know if it helps: <http://www.mathworks.com/matlabcentral/answers/57232-how-to-use-svmtrain-wit...

9 years ago | 0

Selecting important features from a very large pool
You may find these two posts useful: <http://www.mathworks.com/matlabcentral/answers/48633-how-to-find-the-important-features...

9 years ago | 0

Error in kmeans of Matlab R2013 ?
Type which kmeans which randsample to verify that you are using the functions from the official MATLAB installation. ...

9 years ago | 0

| accepted

problem when performing PCA on large dataset
If you can load the dataset into memory, the rest should be easy. Here is how you compute coefficients and scores for wide data ...

9 years ago | 0

How can I define the cost matrix using Classify function for discriminant analysis classification in MATLAB R2009a?
One option is to upgrade. In 11b, we introduced ClassificationDiscriminant which accepts the cost option. Otherwise take a lo...

9 years ago | 0

Create an 'other' category for classregtree?
It is not entirely clear from your post if you are talking about a categorical predictor (one of the variables in X) or the cate...

9 years ago | 0

ClassificationDiscriminant - How to exclude a predictor for only one group level?
Delete the corresponding column in the matrix of predictors you pass to ClassificationDiscriminant.fit: X(:,1) = [];

9 years ago | 1

| accepted

How to do a ROC analysis using Matlab build-in SVM (Not LibSVM)

9 years ago | 7

| accepted

KNN classifier with ROC Analysis
For 3 neighbors, the posterior probability has at most 4 distinct values, namely (0:3)/3. Likely less for the Fisher iris data b...

9 years ago | 1

| accepted

What exactly the ROC curve can tell us or can be inferred?
1. You can report anything you like as long as you report an estimate obtained by cross-validation or using an independent test ...

9 years ago | 2

| accepted

What exactly the ROC curve can tell us or can be inferred?
1-2. You can use either accuracy. The accuracy obtained by LDA is for assigning every observation into the class with the larges...

9 years ago | 1

How to do a classification using Matlab?
If you are using a relatively recent release, I suggest switching to |ClassificationDiscriminant|. It has more functionality and...

9 years ago | 0

| accepted

SVM TRAIN - WARNING ABOUT SINGULAR MATRIX
This warning is thrown by the backslash operator \ when it solves the linear system based on the kernel matrix. You don't need t...

9 years ago | 0

| accepted

How can I find the confusion matrix for a three class problem and thenfind specificity, sensitivity and accuracy from them.
If you have Statistics Toolbox, take a look at the |confusionmat| function. The accuracy is simply the sum of the diagonal eleme...

10 years ago | 0

Euclidean Distance Classifier implementation for classifying 6 expressions
If by "Euclidean distance classifier" you mean nearest neighbor rules, take a look at |ClassificationKNN| in Statistics Toolbox....

10 years ago | 0

| accepted

Supervised Learning, how to examine the model produced
The answer varies per model. For linear types of |ClassificationDiscriminant|, you can use the |DeltaPredictor| property. Thi...

10 years ago | 0

| accepted

SVMTRAIN - LEAST SQUARE METHOD OR QUADRATIC PROGRAMMING METHOD
LS minimizes mean squared error to solve the SVM regression problem. In SVM classification, coefficients alpha are bounded betwe...

10 years ago | 0

| accepted

SVM - SVMTRAIN method SMO (error: No convergence achieved within maximum number of iterations)
You can do 3 things: # Lower the box constraint. # Increase |tolkkt|. # Set |kktviolationlevel| to a positive value. Any...

10 years ago | 0

| accepted

does anybody have expertise with matlab SVM classifier?

10 years ago | 2

| accepted

The |princomp| and |pca| functions center the data but do *not* scale. (In addition, |pca| allows not to center.) The easiest...

10 years ago | 0

How do I find slack variables in SVM?/ Distance to the boundary?
By definition, a slack variable for observation x with label y (-1 or +1) is max(0,1-y*f), where f is the SVM prediction (soft s...

10 years ago | 0