Dense: Regular, densely-connected NN layer.

In kerasR: R Interface to the Keras Deep Learning Library

Regular, densely-connected NN layer.

Description

Dense implements the operation: output = activation(dot(input, kernel) + bias) where activation is the element-wise activation function passed as the activation argument, kernel is a weights matrix created by the layer, and bias is a bias vector created by the layer (only applicable if use_bias is True). Note: if the input to the layer has a rank greater than 2, then it is flattened prior to the initial dot product with kernel.

Usage

Dense(units, activation = "linear", use_bias = TRUE,
  kernel_initializer = "glorot_uniform", bias_initializer = "zeros",
  kernel_regularizer = NULL, bias_regularizer = NULL,
  activity_regularizer = NULL, kernel_constraint = NULL,
  bias_constraint = NULL, input_shape = NULL)

Arguments

units	Positive integer, dimensionality of the output space.
activation	The activation function to use.
use_bias	Boolean, whether the layer uses a bias vector.
kernel_initializer	Initializer for the kernel weights matrix
bias_initializer	Initializer for the bias vector
kernel_regularizer	Regularizer function applied to the kernel weights matrix
bias_regularizer	Regularizer function applied to the bias vector
activity_regularizer	Regularizer function applied to the output of the layer (its "activation").
kernel_constraint	Constraint function applied to the
bias_constraint	Constraint function applied to the bias vector
input_shape	only need when first layer of a model; sets the input shape of the data

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, Dropout, Embedding, Flatten, GaussianNoise, 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(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)
  
  # You can also add layers directly as arguments to Sequential()

  mod <- Sequential(
    Dense(units = 50, input_shape = ncol(X_train)),
    Dropout(rate = 0.5),
    Activation("relu"),
    Dense(units = 3),
    ActivityRegularization(l1 = 1),
    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)
  
}

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(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)
  
  # You can also add layers directly as arguments to Sequential()

  mod <- Sequential(
    Dense(units = 50, input_shape = ncol(X_train)),
    Dropout(rate = 0.5),
    Activation("relu"),
    Dense(units = 3),
    ActivityRegularization(l1 = 1),
    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.