similar to: CVnn2 + nnet question

I hope this question is adequate for this list I use the nnet code from V&R p. 348: The very nice and general function CVnn2() to choose the number of hidden units and the amount of weight decay by an inner cross-validation- with a slight modification to use it for classification (see below). My data has 2 classes with unequal size: 45 observations for classI and 116 obs. for classII With

Dear R-users I use nnet for a classification (2 classes) problem. I use the code CVnn1, CVnn2 as described in V&R. The thing I changed to the code is: I define the (class) weight for each observation in each cv 'bag' and give the vector of weights as parameter of nnet(..weights = weight.vector...) Unfortunately I get an error during some (but not all!) inner-fold cv runs:

Dear R-users, dear Prof. Ripley as package maintainer I tried to investigate the odd error, when I call nnet together with a 'weights' parameter, using the 'fgl' example in V&R p 348 The error I get is: Error in eval(expr, envir, enclos) : Object "w" not found I think it is a kind of scoping problem, but I really cannot see, what the problem exactly is. and

I am faced with a situation wherein I have to use multiple lapply's. The pseudo-code could be approximated to something as below: For each X from i=1 to n For each Y based on j=1 to m For each F from 1 to f Do some calculation based on Fij Store Xi,Yj = Fij End For F End for Y End for X Is there anyway to optimize the processing logic further? I *guess* using the multiple lapply

> nnet.fit<-nnet(as.factor(out) ~ ., data=all_h, size=5, rang=0.3, decay=5e-4, maxit=500) # model fitting > summary(nnet.fit) a 23-5-1 network with 126 weights options were - entropy fitting decay=5e-04 HI, Guys, I can not find the manual to describe how the model is built, is there a more detailed description how nnet package works? -- Sincerely, Changbin -- [[alternative

I am using library(nnet) to train up an ANN with what I believe is a moderately sized dataset, but R is complaining about too many weights: --- > nn.1 <- nnet(t(data), targets, size = 4, rang = 0.1, decay = 5e-4, maxit = 200) Error in nnet.default(t(data), targets, size = 4, rang = 0.1, decay = 5e-04, : Too many (1614) weights > dim(targets) [1] 146 2 > dim(data) ## Note

Hi R-helpers, Can some one tell me how to train 'mynn' of this type?: mynn <- nnet(y ~ x1 + ..+ x8, data = lgist, size = 2, rang = 0.1, decay = 5e-4, maxit = 200) I assume that this nn is untrained, and to train I have to split the original data into train:test data set, do leave-one-out refitting to refine the weights (please straighten this up if I was wrong). I just don't know

The following code fails to train a nnet model in a random dataset using caret: nR <- 700 nCol <- 2000 myCtrl <- trainControl(method="cv", number=3, preProcOptions=NULL, classProbs = TRUE, summaryFunction = twoClassSummary) trX <- data.frame(replicate(nR, rnorm(nCol))) trY <- runif(1)*trX[,1]*trX[,2]^2+runif(1)*trX[,3]/trX[,4] trY <-

Dear all, Objective: I am trying to learn about neural networks. I want to see if i can train an artificial neural network model to discriminate between spam and nonspam emails. Problem: I created my own model (example 1 below) and got an error of about 7.7%. I created the same model using the Rattle package (example 2 below, based on rattles log script) and got a much better error of about

Hi there, I´ve a question concerning the nnet package in the area of survival analysis: what is the final value, which is computed to fit the model with the following nnet-c all: net <- nnet(cat~x, data=d, size=2, decay=0.1, censored=TRUE, maxit=20, Wts=rep(0,22), Hess=TRUE) where cat is a matrix with a row for each record and

Hi, I use nnet for my classification problem and have a problem concerning the calculation of the final value for my validation data.(nnet only calculates the final value for the training data). I made my own final value formula (for the training data I get the same value as nnet): # prob-matrix pmatrix <- cat*fittedValues tmp <- rowSums(pmatrix) # -log likelihood

Dear R people, I want to use the tune.nnet function of e1071 package to tune nnet . I am unable to understand the parameters of tune.nnet from the e1071 pdf document. I have performed nnet on a traindata and want to test it for class prediction with a testdata. I want to know the values of size,decay,range etc. parameters for which the prediction of testdata is best. Can anyone please tell me

HI, Dear R community, My data set has 2409 variables, the last one is response variable. I have used the nnet after feature selection and works. But this time, I am using nnet to fit a model without feature selection. I got the following error information: > dim(train) [1] 1827 2409 nnet.fit<-nnet(as.factor(out) ~ ., data=train, size=3, rang=0.3, decay=5e-4, maxit=500) # model

Hi, there: I am trying nnet as followed: > mg.nnet<-nnet(x=trn3[,r.v[1:100]], y=trn3[,209], size=5, decay = 5e-4, maxit = 200) # weights: 511 initial value 13822.108453 iter 10 value 7408.169201 iter 20 value 7362.201934 iter 30 value 7361.669408 iter 40 value 7361.294379 iter 50 value 7361.045190 final value 7361.038121 converged Error in y - tmp : non-numeric argument to binary operator

Hello ! I'd like to know to which of the FANN package network corresponds the R nnet network ? In more details, what is the R nnet activation function, what is the training algorithm (rprop, quickprop, ...) ? Also, it seems that the R nnet "decay" parameter in nnet corresponds to the "learning_rate" parameter in FANN. Correct ? Many thanks in advance ! Luc Moulinier

Greetings, I am having trouble calculating artificial neural network misclassification errors using errorest() from the ipred package. I have had no problems estimating the values with randomForest() or svm(), but can't seem to get it to work with nnet(). I believe this is due to the output of the predict.nnet() function within cv.factor(). Below is a quick example of the problem I'm

Dear All, After followed the help of nnet, I could get the networks trained and, excitedly, get the prediction for other samples. It is a two classes data set, I used "N" and "P" to label the two. My question is, how do I get the predicted numerical value for each sample? Not just give me the label(either "N" or "P")? Thanks! FYI: The nnet example I

Hi, Dear all, I am just starting using R in my work and got some trouble to figure out some of the errors. Can anybody help me? The following is the script: read.csv('pupil.txt',header=TRUE,sep='\t')->pupil samp<-c(1:50, 112:162, 171:220, 228:278) pupil.nn2 <- nnet(Type ~ ., data = pupil, subset = samp, size = 2, rang = 0.1, decay = 5e-4, maxit = 200)

Hi, I am trying to run a nnet algorithm but when I try to use the predict function with type='class', it gives the following error: fit <- nnet(y~., size = 1, data = train.set, rang = 0.5, maxit=200, decay = 0) predict<-predict(fit,test.set,type='class') Error in predict.nnet(fit, test.set, type = "class") : inappropriate fit for class I couldn't figure

Hi, I am trying to make a neural network learning a "noisy sine wave". Suppose I generate my data like so.. x <- seq(-2*pi, 2*pi, length=500) y <- sin(x) + rnorm(500, sd=sqrt(0.075)) I then train the neural net on the first 400 points using c <- nnet(as.matrix(x[1:400]),as.matrix(y[1:400]), size=3, maxit=10000, abstol=0.075, decay=0.007) Inspecting the fit of the training