TeachNet: Fits neural networks to learn about back propagation

Can fit neural networks with up to two hidden layer and two different error functions. Also able to handle a weight decay. But just able to compute one output neuron and very slow.

Install the latest version of this package by entering the following in R:
install.packages("TeachNet")
AuthorGeorg Steinbuss
Date of publication2014-01-06 17:18:41
MaintainerGeorg Steinbuss <gspam@steinbuss.de>
LicenseGPL (>= 2)
Version0.7

View on CRAN

Functions

accuracy.me Man page
computeGrad1 Man page
computeGrad2 Man page
computeOutput1 Man page
computeOutput2 Man page
confusion Man page
createWeights1 Man page
createWeights2 Man page
crossEntropy Man page
find.Threshold Man page
fitTeachNet1 Man page
fitTeachNet2 Man page
is.acct Man page
is.data Man page
is.decay Man page
is.err Man page
is.learn Man page
is.numberOfNeurons Man page
is.sample Man page
is.sampleLeng Man page
is.stepMax Man page
is.thres.error Man page
logistic Man page
logistic.differential Man page
*,numeric,Weights2-method Man page
*,numeric,Weights-method Man page
predict.Weights Man page
predict.Weights2 Man page
squaredError Man page
sumCrossEntropy Man page
sumSquaredError Man page
TeachNet Man page
TeachNet-package Man page
transformPrediction Man page
Weights2-class Man page
-,Weights2,Weights2-method Man page
+,Weights2,Weights2-method Man page
Weights-class Man page
-,Weights,Weights-method Man page
+,Weights,Weights-method Man page

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.