GaussianNoise: Apply Gaussian noise layer

In kerasR: R Interface to the Keras Deep Learning Library

Apply Gaussian noise layer

Description

The function GaussianNoise applies additive noise, centered around 0 and GaussianDropout applied multiplicative noise centered around 1.

Usage

GaussianNoise(stddev = 1, input_shape = NULL)

GaussianDropout(rate = 0.5, input_shape = NULL)

Arguments

stddev	standard deviation of the random Gaussian
input_shape	only need when first layer of a model; sets the input shape of the data
rate	float, drop probability

Author(s)

Taylor B. Arnold, [e-mail]

References

Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.

See Also

Other layers: Activation, ActivityRegularization, AdvancedActivation, BatchNormalization, Conv, Dense, Dropout, Embedding, Flatten, LayerWrapper, LocallyConnected, Masking, MaxPooling, Permute, RNN, RepeatVector, Reshape, Sequential

Examples

if(keras_available()) {
  X_train <- matrix(rnorm(100 * 10), nrow = 100)
  Y_train <- to_categorical(matrix(sample(0:2, 100, TRUE), ncol = 1), 3)
  
  mod <- Sequential()
  mod$add(Dense(units = 50, input_shape = dim(X_train)[2]))
  mod$add(Dropout(rate = 0.5))
  mod$add(Activation("relu"))
  mod$add(GaussianNoise())
  mod$add(GaussianDropout())
  mod$add(Dense(units = 3))
  mod$add(ActivityRegularization(l1 = 1))
  mod$add(Activation("softmax"))
  keras_compile(mod,  loss = 'categorical_crossentropy', optimizer = RMSprop())
  
  keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5,
            verbose = 0, validation_split = 0.2)
}

kerasR documentation built on Aug. 17, 2022, 5:06 p.m.