Implementation of Unsupervised Neural Architectures


[Up] [Top]

Documentation for package ‘ruta’ version 1.1.0

Help Pages

+.ruta_network Add layers to a network/Join networks
add_weight_decay Add weight decay to any autoencoder
apply_filter Apply filters
apply_filter.ruta_noise_cauchy Apply filters
apply_filter.ruta_noise_gaussian Apply filters
apply_filter.ruta_noise_ones Apply filters
apply_filter.ruta_noise_saltpepper Apply filters
apply_filter.ruta_noise_zeros Apply filters
as_loss Coercion to ruta_loss
as_loss.character Coercion to ruta_loss
as_loss.ruta_loss Coercion to ruta_loss
as_network Coercion to ruta_network
as_network.integer Coercion to ruta_network
as_network.numeric Coercion to ruta_network
as_network.ruta_layer Coercion to ruta_network
as_network.ruta_network Coercion to ruta_network
autoencode Automatically compute an encoding of a data matrix
autoencoder Create an autoencoder learner
autoencoder_contractive Create a contractive autoencoder
autoencoder_denoising Create a denoising autoencoder
autoencoder_robust Create a robust autoencoder
autoencoder_sparse Sparse autoencoder
autoencoder_variational Build a variational autoencoder
c.ruta_network Add layers to a network/Join networks
contraction Contractive loss
conv Create a convolutional layer
correntropy Correntropy loss
decode Retrieve decoding of encoded data
dense Create a fully-connected neural layer
dropout Dropout layer
encode Retrieve encoding of data
encoding_index Get the index of the encoding
evaluate_binary_accuracy Evaluation metrics
evaluate_binary_crossentropy Evaluation metrics
evaluate_kullback_leibler_divergence Evaluation metrics
evaluate_mean_absolute_error Evaluation metrics
evaluate_mean_squared_error Evaluation metrics
evaluation_metric Custom evaluation metrics
generate Generate samples from a generative model
generate.ruta_autoencoder_variational Generate samples from a generative model
input Create an input layer
is_contractive Detect whether an autoencoder is contractive
is_denoising Detect whether an autoencoder is denoising
is_robust Detect whether an autoencoder is robust
is_sparse Detect whether an autoencoder is sparse
is_trained Detect trained models
is_variational Detect whether an autoencoder is variational
layer_keras Custom layer from Keras
load_from Save and load Ruta models
loss_variational Variational loss
make_contractive Add contractive behavior to any autoencoder
make_denoising Add denoising behavior to any autoencoder
make_robust Add robust behavior to any autoencoder
make_sparse Add sparsity regularization to an autoencoder
new_autoencoder Create an autoencoder learner
new_layer Layer wrapper constructor
new_network Sequential network constructor
noise Noise generator
noise_cauchy Additive Cauchy noise
noise_gaussian Additive Gaussian noise
noise_ones Filter to add ones noise
noise_saltpepper Filter to add salt-and-pepper noise
noise_zeros Filter to add zero noise
output Create an output layer
plot.ruta_network Draw a neural network
predict.ruta_autoencoder Retrieve reconstructions for input data
print.ruta_autoencoder Inspect Ruta objects
print.ruta_loss Inspect Ruta objects
print.ruta_loss_named Inspect Ruta objects
print.ruta_network Inspect Ruta objects
reconstruct Retrieve reconstructions for input data
save_as Save and load Ruta models
sparsity Sparsity regularization
to_keras Convert a Ruta object onto Keras objects and functions
to_keras.ruta_autoencoder Extract Keras models from an autoencoder wrapper
to_keras.ruta_autoencoder_variational Extract Keras models from an autoencoder wrapper
to_keras.ruta_filter Get a Keras generator from a data filter
to_keras.ruta_layer_conv Convert Ruta layers onto Keras layers
to_keras.ruta_layer_custom Convert Ruta layers onto Keras layers
to_keras.ruta_layer_dense Convert Ruta layers onto Keras layers
to_keras.ruta_layer_input Convert Ruta layers onto Keras layers
to_keras.ruta_layer_variational Obtain a Keras block of layers for the variational autoencoder
to_keras.ruta_loss_contraction Obtain a Keras loss
to_keras.ruta_loss_correntropy Obtain a Keras loss
to_keras.ruta_loss_named Obtain a Keras loss
to_keras.ruta_loss_variational Obtain a Keras loss
to_keras.ruta_network Build a Keras network
to_keras.ruta_sparsity Translate sparsity regularization to Keras regularizer
to_keras.ruta_weight_decay Obtain a Keras weight decay
train Train a learner object with data
train.ruta_autoencoder Train a learner object with data
variational_block Create a variational block of layers
weight_decay Weight decay
[.ruta_network Access subnetworks of a network