[R] using softmax in nnet

Raji raji.sankaran at gmail.com
Thu Oct 21 06:30:17 CEST 2010


 I run my data in nnet factor response (with 0 & 1
 values) and explicitly put softmax=TRUE. I get the following error.

nn <-
nnet(as.factor(table[,8])~.,data=table,size=2,linout=FALSE,entropy=FALSE,softmax=TRUE,censored=FALSE,rang=0.7,Hess=FALSE,trace=FALSE,MaxNwts=1000,decay=0.1,maxit=1000,skip=FALSE,abstol=1.0e-4,reltol=1.0e-8)
Error in nnet.default(x, y, w, entropy = TRUE, ...) : 
  formal argument "entropy" matched by multiple actual arguments

Cant softmax be used for dichotomous response? i think i am missing out on
something here. Can you please give more insight on this?

Thanks for your help.
-- 
View this message in context: http://r.789695.n4.nabble.com/using-softmax-in-nnet-tp3005013p3005013.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list