Dense layer
This card is a wrapper of this Keras class.
Note: the backend for building and training neural networks is based on Keras. The documentation of this card is a variant of the documentation of its corresponding class.
Inputs
-
Units — Integer
Positive integer, dimensionality of the output space.
-
Activation — String
Activation function to use.
-
Use bias — Boolean
Whether the layer uses a bias vector.
-
Kernel initializer — NeuralNetworkInitializer
Initializer for the kernel weights matrix. If not specified, then Glorot uniform initializer is used.
-
Bias initializer — NeuralNetworkInitializer
Initializer for the bias vector. If not specified, then Zeros initializer is used.
-
Kernel regularizer — NeuralNetworkRegularizer
Regularizer function applied to the kernel weights matrix.
-
Bias regularizer — NeuralNetworkRegularizer
Regularizer function applied to the bias vector.
-
Activity regularizer — NeuralNetworkRegularizer
Regularizer function applied to the output of the layer (its “activation”).
-
Kernel constraint — NeuralNetworkConstraint
Constraint function applied to the kernel weights matrix.
-
Bias constraint — NeuralNetworkConstraint
Constraint function applied to the bias vector.
-
Input — NeuralNetworkTensor
Input of this layer.
Outputs
-
Layer instance — NeuralNetworkLayer
Instance of this layer. It can be wrapped using a Bidirectional or a TimeDistributed wrapper.
-
Output — NeuralNetworkTensor
Output of this layer.