Package for deep architectures and Restricted-Bolzmann-Machines


[Up] [Top]

Documentation for package ‘darch’ version 0.9.1

Help Pages

A B C D F G L M N P Q R S T

darch-package Deep architectures in R

-- A --

addExecOutput Adds an execution output for a DArch object
addExecOutput-method Adds an execution output for a DArch object
addLayer Adds a layer to the DArch object
addLayer-method Adds a layer to the DArch object
addLayerField Adds a field to a layer
addLayerField-method Adds a field to a layer

-- B --

backpropagation Backpropagation learning function
binSigmoidUnit Binary sigmoid unit function.

-- C --

crossEntropyError Cross entropy error function

-- D --

DArch Class for deep architectures
darch Deep architectures in R
DArch-class Class for deep architectures

-- F --

fineTuneDArch Fine tuning function for the deep architecture.
fineTuneDArch-method Fine tuning function for the deep architecture.

-- G --

generateRBMs Generates the rbm's for the pre-training.
generateRBMs-method Generates the rbm's for the pre-training.
generateWeights Generates a weight matrix.
getBatchSize Returns the batch size of the 'Net'.
getBatchSize-method Returns the batch size of the 'Net'.
getCancel Returns the cancel value.
getCancel-method Returns the cancel value.
getCancelMessage Returns the cancel message.
getCancelMessage-method Returns the cancel message.
getErrorFunction Returns the error function of the 'Net'.
getErrorFunction-method Returns the error function of the 'Net'.
getExecOutput Returns the execution output of the layer from the 'DArch' object
getExecOutput-method Returns the execution output of the layer from the 'DArch' object
getExecOutputs Returns the execution output list of the 'DArch' object
getExecOutputs-method Returns the execution output list of the 'DArch' object
getExecuteFunction Returns the function for the execution of the 'DArch' network.
getExecuteFunction-method Returns the function for the execution of the 'DArch' network.
getFF Returns if the weights are saved as ff objects
getFF-method Returns if the weights are saved as ff objects
getFinalMomentum Returns the final momentum of the 'Net'.
getFinalMomentum-method Returns the final momentum of the 'Net'.
getFineTuneFunction Returns the fine tune function for the 'DArch' object.
getFineTuneFunction-method Returns the fine tune function for the 'DArch' object.
getGenWeightFunction Returns the function for generating weight matrices.
getGenWeightFunction-method Returns the function for generating weight matrices.
getHiddenBiases Returns the biases of the hidden units.
getHiddenBiases-method Returns the biases of the hidden units.
getHiddenBiasesInc Returns the update value for the biases of the hidden units.
getHiddenBiasesInc-method Returns the update value for the biases of the hidden units.
getHiddenUnitStates Returns a list with the states of the hidden units.
getHiddenUnitStates-method Returns a list with the states of the hidden units.
getLayer Returns a layer from the 'DArch' object.
getLayer-method Returns a layer from the 'DArch' object.
getLayerField Returns the field of a layer from the 'DArch' object.
getLayerField-method Returns the field of a layer from the 'DArch' object.
getLayerFunction Returns the neuron function of a layer from the 'DArch' object.
getLayerFunction-method Returns the neuron function of a layer from the 'DArch' object.
getLayers Returns the a list of layers from the 'DArch' object.
getLayers-method Returns the a list of layers from the 'DArch' object.
getLayerWeights Returns the weights of a layer from the 'DArch' object.
getLayerWeights-method Returns the weights of a layer from the 'DArch' object.
getLearnRateBiases Returns the learning rate for the bias weigths of the 'DArch' object.
getLearnRateBiases-method Returns the learning rate for the bias weigths of the 'DArch' object.
getLearnRateBiasHidden Returns the learning rate for the hidden biases.
getLearnRateBiasHidden-method Returns the learning rate for the hidden biases.
getLearnRateBiasVisible Returns the learning rate for the visible biases.
getLearnRateBiasVisible-method Returns the learning rate for the visible biases.
getLearnRateWeights Returns the learn rate of the weights.
getLearnRateWeights-method Returns the learn rate of the weights.
getMomentum Returns the momentum of the 'Net'.
getMomentum-method Returns the momentum of the 'Net'.
getMomentumSwitch Returns the momentum switch of the 'Net'.
getMomentumSwitch-method Returns the momentum switch of the 'Net'.
getNumHidden Returns the number of hidden units of the 'RBM'
getNumHidden-method Returns the number of hidden units of the 'RBM'
getNumVisible Returns the number of visible units of the 'RBM'
getNumVisible-method Returns the number of visible units of the 'RBM'
getOutput Returns the output of the 'RBM'
getOutput-method Returns the output of the 'RBM'
getPosPhaseData Returns the data for the positive phaes.
getPosPhaseData-method Returns the data for the positive phaes.
getRBMList Returns a list of 'RBM's of the 'DArch' object.
getRBMList-method Returns a list of 'RBM's of the 'DArch' object.
getStats Returns the list of statistics for the network
getStats-method Returns the list of statistics for the network
getVisibleBiases Returns the biases of the visible units.
getVisibleBiases-method Returns the biases of the visible units.
getVisibleBiasesInc Returns the update value for the biases of the visible units.
getVisibleBiasesInc-method Returns the update value for the biases of the visible units.
getVisibleUnitStates Returns a list with the states of the visible units.
getVisibleUnitStates-method Returns a list with the states of the visible units.
getWeightCost Returns the weigth cost for the training
getWeightCost-method Returns the weigth cost for the training
getWeightInc Returns the update value for the weights.
getWeightInc-method Returns the update value for the weights.
getWeights Returns the weigths of the 'RBM'.
getWeights-method Returns the weigths of the 'RBM'.

-- L --

linearUnit Linear unit function.
linearUnitDerivative Linear unit function with unit derivatives.
linearUnitFunc Calculates the linear neuron output no transfer function
loadDArch Loads a DArch network
loadRBM Loads a RBM network
loadRBMFFWeights Loads weigths and biases for a RBM network from a ffData file.

-- M --

makeStartEndPoints Makes start- and end-points for the batches.
minimize Minimize a differentiable multivariate function.
minimizeAutoencoder Conjugate gradient for a autoencoder network
minimizeClassifier Conjugate gradient for a classification network
mseError Mean quared error function

-- N --

Net Abtract class for neural networks.
Net-class Abtract class for neural networks.
newDArch Constructor function for 'DArch' objects.
newRBM Constructor function for RBM object.

-- P --

preTrainDArch Pre trains a 'DArch' network
preTrainDArch-method Pre trains a 'DArch' network

-- Q --

quadraticError Quadratic error function

-- R --

RBM Class for Restricted-Bolzmann-Machine
RBM-class Class for Restricted-Bolzmann-Machine
rbmUpdate Function for updating the weights and biases of an 'RBM'
readMNIST Function for generating ff files of the MNIST Database
removeLayerField Removes a layer from the 'DArch' object
removeLayerField-method Removes a layer from the 'DArch' object
resetDArch Resets the weights and biases of the 'DArch' object
resetDArch-method Resets the weights and biases of the 'DArch' object
resetExecOutput Resets the output list of the 'DArch' object
resetExecOutput-method Resets the output list of the 'DArch' object
resetRBM Resets the weights and biases of the 'RBM' object
resetRBM-method Resets the weights and biases of the 'RBM' object
rpropagation Resilient-Backpropgation training for deep architectures.
runDArch Execute the darch

-- S --

saveDArch Saves a DArch network
saveDArch-method Saves a DArch network
saveRBM Saves a RBM network
saveRBM-method Saves a RBM network
saveRBMFFWeights Saves weights and biases of a RBM network into a ffData file.
saveRBMFFWeights-method Saves weights and biases of a RBM network into a ffData file.
setBatchSize Sets the batch size of the 'Net'.
setBatchSize<- Sets the batch size of the 'Net'.
setBatchSize<--method Sets the batch size of the 'Net'.
setCancel Set whether the learning shall be canceled.
setCancel<- Set whether the learning shall be canceled.
setCancel<--method Set whether the learning shall be canceled.
setCancelMessage Sets the cancel message.
setCancelMessage<- Sets the cancel message.
setCancelMessage<--method Sets the cancel message.
setErrorFunction Sets the error function of the 'Net'.
setErrorFunction<- Sets the error function of the 'Net'.
setErrorFunction<--method Sets the error function of the 'Net'.
setExecuteFunction Sets the execution function for the network
setExecuteFunction<- Sets the execution function for the network
setExecuteFunction<--method Sets the execution function for the network
setFF Sets if the weights are saved as ff objects
setFF<- Sets if the weights are saved as ff objects
setFF<--method Sets if the weights are saved as ff objects
setFinalMomentum Sets the final momentum of the 'Net'.
setFinalMomentum<- Sets the final momentum of the 'Net'.
setFinalMomentum<--method Sets the final momentum of the 'Net'.
setFineTuneFunction Sets the fine tuning function for the network
setFineTuneFunction<- Sets the fine tuning function for the network
setFineTuneFunction<--method Sets the fine tuning function for the network
setGenWeightFunction Sets the function for generating weight matrices.
setGenWeightFunction<- Sets the function for generating weight matrices.
setGenWeightFunction<--method Sets the function for generating weight matrices.
setHiddenBiases Sets the biases of the hidden units for the 'RBM' object
setHiddenBiases<- Sets the biases of the hidden units for the 'RBM' object
setHiddenBiases<--method Sets the biases of the hidden units for the 'RBM' object
setHiddenBiasesInc Sets the update value for the biases of the hidden units
setHiddenBiasesInc<- Sets the update value for the biases of the hidden units
setHiddenBiasesInc<--method Sets the update value for the biases of the hidden units
setHiddenUnitFunction Sets the unit function of the hidden units
setHiddenUnitFunction<- Sets the unit function of the hidden units
setHiddenUnitFunction<--method Sets the unit function of the hidden units
setHiddenUnitStates Sets the states of the hidden units
setHiddenUnitStates<- Sets the states of the hidden units
setHiddenUnitStates<--method Sets the states of the hidden units
setLayer Sets a layer with the given index for the network
setLayer<- Sets a layer with the given index for the network
setLayer<--method Sets a layer with the given index for the network
setLayerField Sets a field in a layer.
setLayerField<- Sets a field in a layer.
setLayerField<--method Sets a field in a layer.
setLayerFunction Sets the function for a layer with the given index
setLayerFunction<- Sets the function for a layer with the given index
setLayerFunction<--method Sets the function for a layer with the given index
setLayers Sets the layers for the network
setLayers<- Sets the layers for the network
setLayers<--method Sets the layers for the network
setLayerWeights Sets the weights of a layer with the given index
setLayerWeights<- Sets the weights of a layer with the given index
setLayerWeights<--method Sets the weights of a layer with the given index
setLearnRateBiases Sets the learning rate for the biases
setLearnRateBiases<- Sets the learning rate for the biases
setLearnRateBiases<--method Sets the learning rate for the biases
setLearnRateBiasHidden Sets the learnig rates of the biases for the hidden units
setLearnRateBiasHidden<- Sets the learnig rates of the biases for the hidden units
setLearnRateBiasHidden<--method Sets the learnig rates of the biases for the hidden units
setLearnRateBiasVisible Sets the learnig rates of the biases for the visible units
setLearnRateBiasVisible<- Sets the learnig rates of the biases for the visible units
setLearnRateBiasVisible<--method Sets the learnig rates of the biases for the visible units
setLearnRateWeights Sets the learning rate for the weights.
setLearnRateWeights<- Sets the learning rate for the weights.
setLearnRateWeights<--method Sets the learning rate for the weights.
setLogLevel Sets the log level for the 'Net'.
setLogLevel<- Sets the log level for the 'Net'.
setLogLevel<--method Sets the log level for the 'Net'.
setMomentum Sets the momentum of the 'Net'.
setMomentum<- Sets the momentum of the 'Net'.
setMomentum<--method Sets the momentum of the 'Net'.
setMomentumSwitch Sets the momentum switch of the 'Net'.
setMomentumSwitch<- Sets the momentum switch of the 'Net'.
setMomentumSwitch<--method Sets the momentum switch of the 'Net'.
setNumHidden Sets the number of hidden units
setNumHidden<- Sets the number of hidden units
setNumHidden<--method Sets the number of hidden units
setNumVisible Sets the number of visible units
setNumVisible<- Sets the number of visible units
setNumVisible<--method Sets the number of visible units
setOutput Sets the output of the 'RBM' object
setOutput<- Sets the output of the 'RBM' object
setOutput<--method Sets the output of the 'RBM' object
setPosPhaseData Sets the positive phase data for the training
setPosPhaseData<- Sets the positive phase data for the training
setPosPhaseData<--method Sets the positive phase data for the training
setRBMList Sets the list of RBMs
setRBMList<- Sets the list of RBMs
setRBMList<--method Sets the list of RBMs
setStats Adds a list of statistics to the network
setStats<- Adds a list of statistics to the network
setStats<--method Adds a list of statistics to the network
setUpdateFunction Sets the update function of the 'RBM' object
setUpdateFunction<- Sets the update function of the 'RBM' object
setUpdateFunction<--method Sets the update function of the 'RBM' object
setVisibleBiases Sets the biases of the visible units for the 'RBM' object
setVisibleBiases<- Sets the biases of the visible units for the 'RBM' object
setVisibleBiases<--method Sets the biases of the visible units for the 'RBM' object
setVisibleBiasesInc Sets the update value for the biases of the visible units
setVisibleBiasesInc<- Sets the update value for the biases of the visible units
setVisibleBiasesInc<--method Sets the update value for the biases of the visible units
setVisibleUnitFunction Sets the unit function of the visible units
setVisibleUnitFunction<- Sets the unit function of the visible units
setVisibleUnitFunction<--method Sets the unit function of the visible units
setVisibleUnitStates Sets the states of the visible units
setVisibleUnitStates<- Sets the states of the visible units
setVisibleUnitStates<--method Sets the states of the visible units
setWeightCost Sets the weight costs for the training
setWeightCost<- Sets the weight costs for the training
setWeightCost<--method Sets the weight costs for the training
setWeightInc Sets the update values for the weights
setWeightInc<- Sets the update values for the weights
setWeightInc<--method Sets the update values for the weights
setWeights Sets the weights of the 'RBM' object
setWeights<- Sets the weights of the 'RBM' object
setWeights<--method Sets the weights of the 'RBM' object
sigmoidUnit Sigmoid unit function.
sigmoidUnitDerivative Sigmoid unit function with unit derivatives.
sigmUnitFunc Calculates the neuron output with the sigmoid function
sigmUnitFuncSwitch Calculates the neuron output with the sigmoid function
softmaxUnit Softmax unit function.
softmaxUnitDerivative Softmax unit function with unit derivatives.

-- T --

trainRBM Trains a 'RBM' with contrastive divergence
trainRBM-method Trains a 'RBM' with contrastive divergence