how can I constrain weights of linear classifier in MATLAB?

Question

Heeseung Lee 2015-12-23

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/261424-how-can-i-constrain-weights-of-linear-classifier-in-matlab

回答： Rakesh Chavan 2016-1-4

I am graduate student studying system neuroscience in Korea. I have a problem and need your help... problem is like below.

There are a number of neurons and we know their firing rates on -3s, -2s, -1s, like

neuron index :

1 2 3 4

firing rata

         0s:      1     1    -1     1
        -1s:     -1    -1     0    -1
        -2s:      0     0     0     0
        -3s:      1     1     1     1

By using these fire rate history, I want to predict current(0s) firing rate of neurons whether it is 1 or -1. I am using linear SVM and varying weights of each time point. But, I want to constrain absolute value of weight of recent firing rate is always larger than that of past like

weight of

   -1s:  -0.8
   -2s:  0.3
   -3s:  -0.1

How can I realize this idea on linear classifier like linear SVM on MATLAB? (of course, other linear classifier would be welcomed)

please help me...

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Rakesh Chavan 2016-1-4

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/261424-how-can-i-constrain-weights-of-linear-classifier-in-matlab#answer_204982

Hi,

It is possible to create a linear SVM model using the 'fitcsvm' function based on the training data. http://www.mathworks.com/help/stats/fitcsvm.html

You can use the 'predict' function to for classifying new data using a trained SVM classifier: http://www.mathworks.com/help/stats/compactclassificationsvm.predict.html

A general overview of the process is given in the following link: http://www.mathworks.com/help/stats/support-vector-machines-svm.html

For generating a linear discriminant analysis classifier the 'fitcdiscr' can be used. The weights option for this function can be used to specify custom weights. Kindly refer to the following link: http://www.mathworks.com/help/stats/fitcdiscr.html