Apply Gaussian noise layer
The function GaussianNoise applies additive noise, centered around 0 and GaussianDropout applied multiplicative noise centered around 1.
GaussianNoise(stddev = 1, input_shape = NULL) GaussianDropout(rate = 0.5, input_shape = NULL)
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 |
Taylor B. Arnold, taylor.arnold@acm.org
Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.
Other layers: Activation,
ActivityRegularization,
AdvancedActivation,
BatchNormalization, Conv,
Dense, Dropout,
Embedding, Flatten,
LayerWrapper,
LocallyConnected, Masking,
MaxPooling, Permute,
RNN, RepeatVector,
Reshape, Sequential
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)
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.