[R] A Neural Network question

Charles Determan cdetermanjr at gmail.com
Mon Apr 18 15:41:48 CEST 2016


Hi Phil,

I don't think this is the correct list for this.  You question has nothing
to do with R specifically which is the purpose here.  I suggest you pursue
other help lists related to neural networks to try and find someone to
assist you.

Regards,
Charles

On Sat, Apr 16, 2016 at 2:08 AM, Philip Rhoades <phil at pricom.com.au> wrote:

> People,
>
> I thought I needed to have some familiarity with NNs for some of my
> current (non-profit, brain-related) projects so I started looking at
> various programming environments including R and I got this working:
>
>   http://gekkoquant.com/2012/05/26/neural-networks-with-r-simple-example
>
> however I needed pictures to help understand what was going on and then I
> found this:
>
>
> https://jamesmccaffrey.files.wordpress.com/2012/11/backpropagationcalculations.jpg
>
> which I thought was almost intelligible so I had an idea which I thought
> would help the learning process:
>
> - Create a very simple NN implemented as a spreadsheet where each sheet
> would correspond to an iteration
>
> I started doing this on LibreOffice:
>
> - I think am already starting to get a better idea of how NNs work just
> from the stuff I have done on the spreadsheet already
>
> - I have now transferred my LibreOffice SpreadSheet (SS) to a shared
> Google Docs Calc file and can share it for editing with others
>
>
> https://docs.google.com/spreadsheets/d/1eSCgGU5qeI3_PmQhwZn4RH0NznUekVP5BP7w4MpKSUc/pub?output=pdf
>
> - I think I have the SS calculations correct so far except for the stuff
> in the dashed purple box in the diagram
>
> - I am not sure how to implement the purple box . . so I thought I would
> ask for help on this mailing list
>
> If someone can help me with the last bit of the SS, from there I think I
> can then repeat the FR and BP sheets and see how the Diffs evolve . .
>
> Is anyone interested in helping to get this last bit of the spreadsheet
> working so I can move on to doing actual work with the R packages with
> better understanding?
>
> Thanks,
>
> Phil.
> --
> Philip Rhoades
>
> PO Box 896
> Cowra  NSW  2794
> Australia
> E-mail:  phil at pricom.com.au
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

	[[alternative HTML version deleted]]



More information about the R-help mailing list