darch: Package for Deep Architectures and Restricted Boltzmann Machines
Version 0.12.0

The darch package is built on the basis of the code from G. E. Hinton and R. R. Salakhutdinov (available under Matlab Code for deep belief nets). This package is for generating neural networks with many layers (deep architectures) and train them with the method introduced by the publications "A fast learning algorithm for deep belief nets" (G. E. Hinton, S. Osindero, Y. W. Teh (2006) ) and "Reducing the dimensionality of data with neural networks" (G. E. Hinton, R. R. Salakhutdinov (2006) ). This method includes a pre training with the contrastive divergence method published by G.E Hinton (2002) and a fine tuning with common known training algorithms like backpropagation or conjugate gradients. Additionally, supervised fine-tuning can be enhanced with maxout and dropout, two recently developed techniques to improve fine-tuning for deep learning.

Browse man pages Browse package API and functions Browse package files

AuthorMartin Drees [aut, cre, cph], Johannes Rueckert [ctb], Christoph M. Friedrich [ctb], Geoffrey Hinton [cph], Ruslan Salakhutdinov [cph], Carl Edward Rasmussen [cph],
Date of publication2016-07-20 00:33:10
MaintainerMartin Drees <mdrees@stud.fh-dortmund.de>
LicenseGPL (>= 2) | file LICENSE
Version0.12.0
URL https://github.com/maddin79/darch
Package repositoryView on CRAN
InstallationInstall the latest version of this package by entering the following in R:
install.packages("darch")

Man pages

addLayer: Adds a layer to the 'DArch' object
addLayer-DArch-method: Adds a layer to the 'DArch' object
addLayerField: Adds a field to a layer
addLayerField-DArch-method: Adds a field to a layer
backpropagation: Backpropagation learning function
contr.ltfr: Wrapper for 'contr.ltfr'
createDataSet: Create data set using data, targets, a formula, and possibly...
createDataSet-ANY-ANY-missing-DataSet-method: Create new 'DataSet' by filling an existing one with new...
createDataSet-ANY-ANY-missing-missing-method: Create 'DataSet' using data and targets.
createDataSet-ANY-missing-formula-missing-method: Constructor function for 'DataSet' objects.
crossEntropyError: Cross entropy error function
darch: Fit a deep neural network
darchBench: Benchmarking wrapper for 'darch'
DArch-class: Class for deep architectures
darchModelInfo: Creates a custom caret model for 'darch'.
darchTest: Test classification network.
DataSet: Class for specifying datasets.
exponentialLinearUnit: Exponential linear unit (ELU) function with unit derivatives.
fineTuneDArch: Fine tuning function for the deep architecture
fineTuneDArch-DArch-method: Fine tuning function for the deep architecture
generateDropoutMask: Dropout mask generator function.
generateRBMs-DArch-method: Generates the RBMs for the pre-training.
generateWeightsGlorotNormal: Glorot normal weight initialization
generateWeightsGlorotUniform: Glorot uniform weight initialization
generateWeightsHeNormal: He normal weight initialization
generateWeightsHeUniform: He uniform weight initialization
generateWeightsNormal: Generates a weight matrix using rnorm.
generateWeightsUniform: Generates a weight matrix using runif
getDropoutMask: Returns the dropout mask for the given layer
getMomentum: Returns the current momentum of the 'Net'.
linearUnit: Linear unit function with unit derivatives.
linearUnitRbm: Calculates the linear neuron output no transfer function
loadDArch: Loads a DArch network
makeStartEndPoints: Makes start- and end-points for the batches.
maxoutUnit: Maxout / LWTA unit function
maxoutWeightUpdate: Updates the weight on maxout layers
minimize: Minimize a differentiable multivariate function.
minimizeAutoencoder: Conjugate gradient for a autoencoder network
minimizeClassifier: Conjugate gradient for a classification network
mseError: Mean squared error function
Net: Abstract class for neural networks.
newDArch: Constructor function for 'DArch' objects.
plot.DArch: Plot 'DArch' statistics or structure.
predict.DArch: Forward-propagate data.
preTrainDArch: Pre-trains a 'DArch' network
preTrainDArch-DArch-method: Pre-trains a 'DArch' network
print.DArch: Print 'DArch' details.
provideMNIST: Provides MNIST data set in the given folder.
RBM: Class for restricted Boltzmann machines
rbmUpdate: Function for updating the weights and biases of an 'RBM'
readMNIST: Function for generating .RData files of the MNIST Database
rectifiedLinearUnit: Rectified linear unit function with unit derivatives.
resetRBM: Resets the weights and biases of the 'RBM' object
rmseError: Root-mean-square error function
rpropagation: Resilient backpropagation training for deep architectures.
runDArch: Forward-propagates data through the network
runDArchDropout: Forward-propagate data through the network with dropout...
saveDArch: Saves a DArch network
setDarchParams: Set 'DArch' parameters
setDropoutMask-set: Set the dropout mask for the given layer.
setLogLevel: Set the log level.
show-DArch-method: Print 'DArch' details.
sigmoidUnit: Sigmoid unit function with unit derivatives.
sigmoidUnitRbm: Calculates the RBM neuron output with the sigmoid function
softmaxUnit: Softmax unit function with unit derivatives.
softplusUnit: Softplus unit function with unit derivatives.
tanhUnit: Continuous Tan-Sigmoid unit function.
tanhUnitRbm: Calculates the neuron output with the hyperbolic tangent...
trainRBM: Trains an 'RBM' with contrastive divergence
validateDataSet: Validate 'DataSet'
validateDataSet-DataSet-method: Validate 'DataSet'
weightDecayWeightUpdate: Updates the weight using weight decay.

Functions

DArch-class Man page
DataSet-class Man page
Net-class Man page
RBM-class Man page
addLayer Man page
addLayer,DArch-method Man page
addLayerField Man page
addLayerField,DArch-method Man page
applyDropoutMaskCpp Source code
autosave Source code
backpropagation Man page Source code
bootstrapDataSet Source code
calculateMomentum Source code
characterToFunction Source code
compatibilityList Source code
configureDArch Source code
contr.ltfr Man page Source code
createAllPlots Source code
createDataSet Man page
createDataSet,ANY,ANY,missing,DataSet-method Man page
createDataSet,ANY,ANY,missing,missing-method Man page
createDataSet,ANY,missing,formula,missing-method Man page
createDataSet.DataSet Man page Source code
createDataSet.default Man page Source code
createDataSet.formula Man page Source code
createPlotErrorClass Source code
createPlotErrorRaw Source code
createPlotMomentum Source code
createPlotTime Source code
crossEntropyError Man page Source code
darch Man page Source code
darch.DataSet Man page Source code
darch.default Man page Source code
darch.formula Man page Source code
darchBench Man page Source code
darchModelInfo Man page Source code
darchTest Man page Source code
deparseClean Source code
ditherCpp Source code
exponentialLinearUnit Man page Source code
exponentialLinearUnitCpp Source code
fineTuneDArch Man page
fineTuneDArch,DArch-method Man page
functionToCharacter Source code
generateDropoutMask Man page Source code
generateDropoutMasksForDarch Source code
generateRBMs,DArch-method Man page
generateWeightsGlorotNormal Man page Source code
generateWeightsGlorotUniform Man page Source code
generateWeightsHeNormal Man page Source code
generateWeightsHeUniform Man page Source code
generateWeightsNormal Man page Source code
generateWeightsUniform Man page Source code
getDropoutMask Man page
getErrorFunctionName Source code
getMomentum Man page
getParameter Source code
helper.printErrorRates Source code
is.logical.length1 Source code
linearUnit Man page Source code
linearUnitRbm Man page Source code
loadDArch Man page Source code
logNamedList Source code
makeStartEndPoints Man page Source code
maxoutUnit Man page Source code
maxoutUnitCpp Source code
maxoutWeightUpdate Man page Source code
maxoutWeightUpdateCpp Source code
mergeParams Source code
minimize Man page Source code
minimizeAutoencoder Man page Source code
minimizeClassifier Man page Source code
minimizeCpp Source code
mseError Man page Source code
newDArch Man page Source code
normalizeWeightsCpp Source code
performBenchmark Source code
plot.DArch Man page Source code
postProcessDataSet Source code
preProcessData Source code
preTrainDArch Man page
preTrainDArch,DArch-method Man page
predict.DArch Man page Source code
prepareBenchmarkDirectory Source code
print.DArch Man page Source code
printDarchParams.backpropagation Source code
printDarchParams.fineTuneDArch Source code
printDarchParams.global Source code
printDarchParams.minimizeAutoencoder Source code
printDarchParams.minimizeClassifier Source code
printDarchParams.preProc Source code
printDarchParams.preTrainDArch Source code
printDarchParams.rpropagation Source code
printDummyVarsFactors Source code
printParams Source code
processAdditionalParams Source code
processParams Source code
provideMNIST Man page Source code
rbmUpdate Man page Source code
readMNIST Man page Source code
rectifiedLinearUnit Man page Source code
rectifiedLinearUnitCpp Source code
resetRBM Man page
rmseError Man page Source code
rpropDeltaCpp Source code
rpropDeltaWiRpropPlus Source code
rpropGradientsCpp Source code
rpropagation Man page Source code
runDArch Man page Source code
runDArchDropout Man page Source code
saveDArch Man page Source code
setDarchParams Man page Source code
setDropoutMask<- Man page
setLogLevel Man page Source code
show,DArch-method Man page
sigmoidUnit Man page Source code
sigmoidUnitCpp Source code
sigmoidUnitRbm Man page Source code
simplifyDataFrame Source code
softmaxUnit Man page Source code
softmaxUnitCpp Source code
softplusUnit Man page Source code
softplusUnitCpp Source code
tanhUnit Man page Source code
tanhUnitRbm Man page Source code
testDArch Source code
trainRBM Man page
validateDataSet Man page
validateDataSet,DataSet-method Man page
weightDecayWeightUpdate Man page Source code
writePlot Source code

Files

inst
inst/CITATION
src
src/minimize.cpp
src/rpropagation.cpp
src/darchUnitFunctions.cpp
src/maxout.cpp
src/normalizeWeights.cpp
src/dither.cpp
src/applyDropoutMask.cpp
src/RcppExports.cpp
NAMESPACE
R
R/bootstrap.R
R/darchUnitFunctions.R
R/net.Class.R
R/plot.R
R/darch.R
R/rbm.Reset.R
R/log.R
R/predict.R
R/darch.Getter.R
R/momentum.R
R/newDArch.R
R/mnist.R
R/net.Getter.R
R/dropout.R
R/benchmark.R
R/darch.Learn.R
R/autosave.R
R/rbmUnitFunctions.R
R/generateWeightsFunctions.R
R/test.R
R/rpropagation.R
R/RcppExports.R
R/print.R
R/makeStartEndPoints.R
R/config.R
R/params.R
R/backpropagation.R
R/dataset.R
R/darch.Add.R
R/darch.Setter.R
R/minimizeAutoencoder.R
R/rbmUpdate.R
R/runDArch.R
R/generateRBMs.R
R/minimizeClassifier.R
R/util.R
R/errorFunctions.R
R/minimize.R
R/darch.Class.R
R/compat.R
R/saveDArch.R
R/loadDArch.R
R/rbm.Learn.R
R/weightUpdateFunctions.R
R/rbm.Class.R
R/caret.R
MD5
README
DESCRIPTION
man
man/rectifiedLinearUnit.Rd
man/exponentialLinearUnit.Rd
man/resetRBM.Rd
man/RBM.Rd
man/getDropoutMask.Rd
man/minimizeClassifier.Rd
man/DataSet.Rd
man/darchBench.Rd
man/makeStartEndPoints.Rd
man/createDataSet-ANY-ANY-missing-missing-method.Rd
man/generateWeightsHeNormal.Rd
man/show-DArch-method.Rd
man/maxoutUnit.Rd
man/crossEntropyError.Rd
man/generateWeightsGlorotUniform.Rd
man/rmseError.Rd
man/darch.Rd
man/darchModelInfo.Rd
man/addLayer-DArch-method.Rd
man/generateDropoutMask.Rd
man/tanhUnit.Rd
man/addLayer.Rd
man/generateWeightsHeUniform.Rd
man/validateDataSet.Rd
man/saveDArch.Rd
man/rpropagation.Rd
man/Net.Rd
man/maxoutWeightUpdate.Rd
man/generateWeightsNormal.Rd
man/createDataSet-ANY-missing-formula-missing-method.Rd
man/runDArch.Rd
man/preTrainDArch-DArch-method.Rd
man/predict.DArch.Rd
man/generateRBMs-DArch-method.Rd
man/sigmoidUnitRbm.Rd
man/linearUnit.Rd
man/print.DArch.Rd
man/softmaxUnit.Rd
man/linearUnitRbm.Rd
man/preTrainDArch.Rd
man/fineTuneDArch.Rd
man/createDataSet-ANY-ANY-missing-DataSet-method.Rd
man/tanhUnitRbm.Rd
man/minimizeAutoencoder.Rd
man/contr.ltfr.Rd
man/readMNIST.Rd
man/setLogLevel.Rd
man/trainRBM.Rd
man/validateDataSet-DataSet-method.Rd
man/provideMNIST.Rd
man/loadDArch.Rd
man/softplusUnit.Rd
man/rbmUpdate.Rd
man/getMomentum.Rd
man/addLayerField.Rd
man/mseError.Rd
man/fineTuneDArch-DArch-method.Rd
man/newDArch.Rd
man/addLayerField-DArch-method.Rd
man/DArch-class.Rd
man/plot.DArch.Rd
man/weightDecayWeightUpdate.Rd
man/sigmoidUnit.Rd
man/minimize.Rd
man/generateWeightsGlorotNormal.Rd
man/createDataSet.Rd
man/setDarchParams.Rd
man/generateWeightsUniform.Rd
man/backpropagation.Rd
man/setDropoutMask-set.Rd
man/darchTest.Rd
man/runDArchDropout.Rd
LICENSE
darch documentation built on May 19, 2017, 6:33 p.m.