Question: brnn package (Bayesian regularization for feed-forward neural networks)
0
gravatar for elisa.micarelli
16 months ago by
European Union
elisa.micarelli10 wrote:

Hi,

I'm using the "brnn" package (Bayesian Regularized Neural Networks), in particular I run the train() function from caret package. My data are stored in a data.frame object and I run the caret function using the "formula" way y ~. (in the "point" there are seven variables that we can call here x1,x2,x3....x7) I would like to understand how to write the formula of brnn method using the values obtained from R. I obtained the following results.

  • MY_results$Model$finalModel$theta
  • MY_results$Model$finalModel$alpha
  • MY_results$Model$finalModel$beta
  • MY_results$Model$finalModel$gamma
  • MY_results$Model$finalModel$Ed
  • MY_results$Model$finalModel$Ew
  • MY_results$Model$finalModel$F_history
  • MY_results$Model$finalModel$reason
  • MY_results$Model$finalModel$epoch
  • MY_results$Model$finalModel$neurons
  • MY_results$Model$finalModel$p
  • MY_results$Model$finalModel$n
  • MY_results$Model$finalModel$npar
  • MY_results$Model$finalModel$x_normalized
  • MY_results$Model$finalModel$x_base
  • MY_results$Model$finalModel$x_spread
  • MY_results$Model$finalModel$y_base
  • MY_results$Model$finalModel$y_spread
  • MY_results$Model$finalModel$y
  • MY_results$Model$finalModel$normalize
  • MY_results$Model$finalModel$call
  • MY_results$Model$finalModel$xNames
  • MY_results$Model$finalModel$problemType
  • MY_results$Model$finalModel$tuneValue
  • MY_results$Model$finalModel$obsLevels
  • MY_results$Model$finalModel$param

I tried to reproduce the brnn formula described inĀ https://cran.r-project.org/web/packages/brnn/brnn.pdf, but I'm not sure how to consider variables x1,x2....x7.

Thank you in advance for any kind of suggestions.

Elisa

R caret machine learning brnn • 379 views
ADD COMMENTlink written 16 months ago by elisa.micarelli10
Please log in to add an answer.

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 16.09
Traffic: 520 users visited in the last hour