Activation Functions about RELU

[niceguy1575]

Hi. I am making use of elman neural networks.

I want to use RELU FUNCTIONs on networks... but, there's no RELU Function on RSNNS

Which options could I use, if I wnat to use RELU Function?

If it is impossible, can I make a pull requests about RELU Function? (Because, I don't know how to use/test my c++ RELU code, and also dependencies...)

Please Let me know..! I really want your help.

[cbergmeir]

Hi,

sounds good, I would be certainly happy about a pull request. Any example code that you might have could be added in the "demo" folder of the package.

Regards, Christoph

On 27/03/18 21:51, LEE JONGWON wrote:

Hi. I am making use of elman neural networks.

I want to use RELU FUNCTIONs on networks... but, there's no RELU Function on RSNNS

Which options could I use, if I wnat to use RELU Function?

If it is impossible, can I make a pull requests about RELU Function? (Because, I don't know how to use/test my c++ RELU code, and also dependencies...)

Please Let me know..! I really want your help.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/cbergmeir/RSNNS/issues/17, or mute the thread https://github.com/notifications/unsubscribe-auth/AAf_GtGwqrmsuO34z0YK7XFeBDmzaTGMks5tikPKgaJpZM4S89l6.

[niceguy1575]

ok Thanks. So to make the purpose, what files should I change? Now I am changing..

1.trans_f.cpp

2. trans_f.h 3.func_tbl.cpp

anything else that I can change ?

[cbergmeir]

Hi,

sounds good, I think this should be everything you need to change.

Regards, Christoph

On 28/03/18 13:33, LEE JONGWON wrote:

ok Thanks. So to make the purpose, what files should I change? Now I am changing..

1.trans_f.cpp

2. trans_f.h 3.func_tbl.cpp

anything else that I can change ?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/cbergmeir/RSNNS/issues/17#issuecomment-376766931, or mute the thread https://github.com/notifications/unsubscribe-auth/AAf_Gq9o2yb_6Uyu8bU1wewZECSysUVJks5tiyDGgaJpZM4S89l6.

[otluiz]

Hello. I making use MSE 'error' (Mean Squared Error) but the function: plotIterativeError(model) ## Summed Squared Error - SSE Its possible change in source code or a making use "work around"? I like add news functionality, with newer error function (and graphics) too. Its possible? Thanks Mr. Cbergmeir.

[cbergmeir]

Hi, the function is implemented here, starting line 171. It should be as simple as dividing object$IterativeFitError by nrow(as.matrix(object$fitted.values)) to get the MSE from the SSE.