(no subject)

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

(no subject)

Omar Maghawry
Hi, I am Omar Maghawry Ibrahim. I am a professor of crop science at SRTA
City, Egypt. I developed a new method to compute relative importance of
inputs in neural networks. I wrote  a code in visual basic for this method
and I published it in a paper in 2013. It produces more accurate results
than Olden and Garson methods especially when inputs have negative
correlation with the output. I hope that this method to be included in R in
the near future.
kindly find the attached paper.
Best regards,
Omar
_______________________________________________
R-sig-ecology mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
Reply | Threaded
Open this post in threaded view
|

Re: (no subject)

Sarah Goslee
Hello Omar,

This doesn't seem particularly ecology-related, but I'll give you the
same answer you're likely to get on any other list.

R is Open Source, and has a vibrant user community. That means that
the best way for you to have your code incorporated into R is to write
a package, and contribute it to CRAN.

If you don't want to do it yourself, you could find a collaborator to
do the R portion, but a package is the only way this is likely to be
included, in the near or far futures.

One place to start might be to look at who has published related
packages, and inquire if they would be interested in collaborating
with you to add your algorithm.

Best,
Sarah

On Tue, Dec 17, 2019 at 1:13 PM Omar Maghawry <[hidden email]> wrote:

>
> Hi, I am Omar Maghawry Ibrahim. I am a professor of crop science at SRTA
> City, Egypt. I developed a new method to compute relative importance of
> inputs in neural networks. I wrote  a code in visual basic for this method
> and I published it in a paper in 2013. It produces more accurate results
> than Olden and Garson methods especially when inputs have negative
> correlation with the output. I hope that this method to be included in R in
> the near future.
> kindly find the attached paper.
> Best regards,
> Omar
> _______________________________________________
> R-sig-ecology mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology



--
Sarah Goslee (she/her)
http://www.numberwright.com

_______________________________________________
R-sig-ecology mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology