I want to work with machine learning in Mathematica. Are there any SVM algorithms implemented in Mathematica anywhere? Or any other algorithms for machine learning? With positive and negative database of HOG descriptors.
-
$\begingroup$ May you could i) give us a reference ii) give it a shot? $\endgroup$ – chris Nov 21 '12 at 14:01
-
$\begingroup$ There's this wolfram.com/products/applications/neuralnetworks 35GBP for students. Haven't used it myself I usually export the data and handle it in matlab since I have the neural networks package for matlab. It makes me cry every time EDIT: Can't find anything about SVM in the Mathematica neural networks package, perhaps it doesn't even have it $\endgroup$ – ssch Nov 21 '12 at 14:43
-
$\begingroup$ What do you mean by "positive and negative database"? $\endgroup$ – Sjoerd C. de Vries Nov 21 '12 at 14:44
$\begingroup$
$\endgroup$
As of Version 10 , Mathematica has a built in function Classify, which implements support vector machines and some other common machine learning algorithms.
trainingset = {1 -> "A", 2 -> "A", 3.5 -> "B", 4 -> "B"};
classifier = Classify[ trainingset, Method -> "SupportVectorMachine"];
$\begingroup$
$\endgroup$
The Mathematica Journal has a nice article on SVM's: A Flexible Implementation for Support Vector Machines, with an accompanying notebook and .m file providing an SVM implementation.
-
$\begingroup$ Calls to the defunct
RandomArray
can be replaced with identical ones toRandomReal
in the example SVM notebook. $\endgroup$ – image_doctor Nov 21 '12 at 14:59 -
2$\begingroup$ There's a (newer?) version of the package on google code: code.google.com/p/prpackage/source/browse/t/draft/classify/… $\endgroup$ – Niki Estner Nov 21 '12 at 15:01
-
$\begingroup$ Would it be too much to ask for a break down of this code? $\endgroup$ – SumNeuron Dec 5 '17 at 11:46