[datatable-help] ELMAN NETWORK IN RSNNS

[JAKE88]

I am new to R and neural networks . So I trained and predicted an elman
network like so :

require ( RSNNS )
mydata = read.csv("mydata.csv",header = TRUE)
mydata.train = mydata[1000:7000,]
mydata.test = mydata[800:999,]

fit <- elman ( mydata.train[,2:19],mydata.train[,1], size =100 
     learnFuncParams =c (0.1) , maxit =1000)
pred <-predict (fit , mydata.test[,2:19])
so pred contains the predictions . The problem I am having is that When I
run pred <-predict (fit , mydata.test[1,2:19]) i.e. on a specific data item
, it doesn't give me the same prediction as in the previous batch . In fact
, each call to predict produces a different result ! Should it not give me
the same result ? The weights and everything are set and it should give the
same result everytime , no ? Or are the batch predictions somehow depending
on each other ?





--
View this message in context: http://r.789695.n4.nabble.com/ELMAN-NETWORK-IN-RSNNS-tp4718063.html
Sent from the datatable-help mailing list archive at Nabble.com.