Activation function / neuron non-linearity
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer.

Gradient updater configuration, for the biases only.

Set constraints to be applied to all layers.

Sets the convolution mode for convolutional layers, which impacts padding and output sizes.

Set the DataType for the network parameters and activations.

Dropout probability.

Gradient normalization strategy.

This method defines Workspace mode being used during inference:
NONE: workspace won't be used
ENABLED: workspaces will be used for inference (reduced memory and better performance)

L1 regularization coefficient for the bias.

L2 regularization coefficient for the bias.

Maximum number of line search iterations.

Objective function to minimize or maximize cost function Default set to minimize true.

Set the regularization for the parameters (excluding biases) - for example WeightDecay
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer.

Random number generator seed.

This method defines Workspace mode being used during training:
NONE: workspace won't be used
ENABLED: workspaces will be used for training (reduced memory and better performance)

Deprecated. 

Add weight decay regularization for the network parameters (excluding biases).

Weight decay for the biases only - see weightDecay(double) for more details
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer.

Weight initialization scheme to use, for initial weight values Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer.

Set the weight noise (such as DropConnect and WeightNoise) for the layers in this network.