How does newrb choose data center?

Hi, I am studying on RBFNN, and I have read about K-mean, OLS to determine the center. But when I use the function newrb, there this no need to determine how to choose the center. I want to know how does the function newrb choose data center, and how it works. Looking for your help! Thanks!

[lc lc]

I have been puzzled by this problem for a long time. Can we discuss the problem together? This is my email:[e-mail]. Thank you!

Answer 1

[the cyclist]

I don't have the Neural Net Toolbox, so I can't check this, but if you type

edit newrb

then you might be able to see the code that does the calculation. There is also often a citation to the literature in the comments at the top of the code.

Be careful not to accidentally make any changes to the file.

[Xiaoran Li]

Thank you. I have tried to understand the code, but it is a little difficult for me. I will read the comments more carefully. Thank you so much!

[Xiaoran Li]

I have found that MATLAB choose center from the train data.Thanks!

Answer 2

[Greg Heath]

See my NEWSGROUP tutorials on NEWRB. Search with

 Greg newrb

1. Forward Search: At the end of each epoch the input with the highest error is added as a Gaussian center.

I have also experimented with other strategies including

2. Backward Search: Start with all inputs as Gaussian centers. Then systematically remove the input with the lowest error rate.

3&4. Forward-Backward and Backward-Forward search

Hope this helps.

Thank you for formally accepting my answer

Greg