Package for Deep Architectures and Restricted Boltzmann Machines

[Up] [Top]

Documentation for package ‘darch’ version 0.12.0

Help Pages

backpropagation Backpropagation learning function
crossEntropyError Cross entropy error function
darch Fit a deep neural network
darch.DataSet Fit a deep neural network
darch.default Fit a deep neural network
darch.formula Fit a deep neural network
darchBench Benchmarking wrapper for 'darch'
darchModelInfo Creates a custom caret model for 'darch'.
darchTest Test classification network.
exponentialLinearUnit Exponential linear unit (ELU) function with unit derivatives.
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
linearUnit Linear unit function with unit derivatives.
maxoutUnit Maxout / LWTA unit function
maxoutWeightUpdate Updates the weight on maxout layers
minimizeAutoencoder Conjugate gradient for a autoencoder network
minimizeClassifier Conjugate gradient for a classification network
mseError Mean squared error function
plot.DArch Plot 'DArch' statistics or structure.
predict.DArch Forward-propagate data.
print.DArch Print 'DArch' details.
provideMNIST Provides MNIST data set in the given folder.
rectifiedLinearUnit Rectified linear unit function with unit derivatives.
rmseError Root-mean-square error function
rpropagation Resilient backpropagation training for deep architectures.
sigmoidUnit Sigmoid unit function with unit derivatives.
softmaxUnit Softmax unit function with unit derivatives.
softplusUnit Softplus unit function with unit derivatives.
tanhUnit Continuous Tan-Sigmoid unit function.
weightDecayWeightUpdate Updates the weight using weight decay.