# [R] R-neuralnet code

arun smartpink111 at yahoo.com
Tue Jul 31 07:14:40 CEST 2012

Hello Rahul,
I can see comments for each line of the code which is not very hard to understand.

From your earlier post, I think you were having some problems with the compute method.  Check this link (http://stackoverflow.com/questions/4891899/how-to-predict-new-cases-using-the-neuralnet-package).  Also, read the neuralnet package.

1.http://rgm2.lab.nig.ac.jp/RGM2/func.php?rd_id=neuralnet:neuralnet-package.
2. http://stackoverflow.com/questions/10939591/predicting-class-for-new-data-using-neuralnet

Hope it helps.
A.K.

________________________________

From: Rahul Bhalla <rahulbhalla_3521 at yahoo.com>
To: arun <smartpink111 at yahoo.com>
Sent: Tuesday, July 31, 2012 12:51 AM
Subject: Re: R-neuralnet code

Thank you for the link but it is not completely convey the concept of neural networks what i need is a simpler code with the interpretation about the GW plots and also if you can give me the interpretation of this code

#install.packages('neuralnet')
library("neuralnet")
#Going to create a neural network to perform sqare rooting
#Generate 50 random numbers uniformly distributed between 0 and 100
#And store them as a dataframe
traininginput <-  as.data.frame(runif(50, min=0, max=100))
trainingoutput <- sqrt(traininginput)

#Column bind the data into one variable
trainingdata <- cbind(traininginput,trainingoutput)
colnames(trainingdata) <-
c("Input","Output")

#Train the neural network
#Going to have 10 hidden layers
#Threshold is a numeric value specifying the threshold for the partial
#derivatives of the error function as stopping criteria.
net.sqrt <- neuralnet(Output~Input,trainingdata, hidden=3, threshold=0.01)
print(net.sqrt)

#Plot the neural network
plot(net.sqrt)

#Test the neural network on some training data
testdata <- as.data.frame((1:10)^2) #Generate some squared numbers
net.results <- compute(net.sqrt, testdata) #Run them through the neural network

________________________________
From: arun <smartpink111 at yahoo.com>
To: Rahul Bhalla <rahulbhalla_3521 at yahoo.com>
Cc: R help <r-help at r-project.org>
Sent: Tuesday, July 31, 2012 1:37 AM
Subject: Re: R-neuralnet code

Hello,

You can check this link (http://econometricsense.blogspot.com/2010/12/r-code-example-for-neural-networks.html).

A.K.

________________________________
From: Rahul Bhalla <rahulbhalla_3521 at yahoo.com>
To: arun <smartpink111 at yahoo.com>
Sent: Monday, July 30, 2012 3:51 PM
Subject: R-neuralnet code

Can you please give me a simple R-neuralnet code and its interpretation.Also the concept of the compute function.

________________________________
From: arun <smartpink111 at yahoo.com>
To: Alaios <alaios at yahoo.com>
Cc: R
help <r-help at r-project.org>
Sent: Monday, July 30, 2012 5:34 PM
Subject: Re: [R] Convert variable to STring

Hello,

Not sure whether this is what you need.

colnames(mymatrix)<-c("function1","function2","function3")
> toString(colnames(mymatrix))
#[1] "function1, function2, function3"

A.K.

----- Original Message -----
From: Alaios <alaios at yahoo.com>
To: R help <R-help at r-project.org>
Cc:
Sent: Monday, July 30, 2012 6:47 AM
Subject: [R] Convert variable to STring

Dear all,
I have a variable that I would like also to use it as a string. The reasons is that I want to collect results from different function to one table.. So
when I use the
colnames(mymatrix) <-c(function1.function2,function3)
the function1, function2, function3 to be "converted" to simple strings so as

colnames(mymatrix)
<-c("function1","function2","function3")

Regards

[[alternative HTML version deleted]]

______________________________________________
R-help at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help