Support Vector Machine could not fix this problem

2 次查看（过去 30 天）
S1 Ekstensi ILKOM
S1 Ekstensi ILKOM 2014-1-10
编辑： Walter Roberson 2014-1-11
i try to using SVM to solve iris classication problem found in matlab dataset, here is what i type:
load irisdataset;
virginincaGroups = ismember(species, 'virginica');
svmStruct = svmtrain(irisInputs, virginicaGroups, 'Kernel_Function', 'rbf', 'boxconstraint', Inf, 'showplot', true)
and the result was
unable to solve this problem due to max iteration
so what is going on???

请先登录，再回答此问题。

回答（1 个）

Shashank Prasanna
Shashank Prasanna 2014-1-10
The iris dataset is 3 classes. The SVMTRAIN function in the Statistics Toolbox can only solve binary classification problems. However, you are free to change the max iteration using the 'options' input. Take a look at the documentation of svmtrain:
http://www.mathworks.com/help/stats/svmtrain.html#namevaluepairarguments
Alternatively, I encourage you to explore other machine learning algorithms that can solve a multi-class classification problem. The following link demonstrates 4 different classifiers:
http://www.mathworks.com/machine-learning/examples.html?file=/products/demos/machine-learning/decision_surface/decision_surface.html

类别

在 Help Center 和 File Exchange 中查找有关 Statistics and Machine Learning Toolbox 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by