Documentation of 'org.neuroph.nnet.comp.layer.InputMapsLayer' Java class
InputMapsLayer
org.neuroph.nnet.comp.layer

Class InputMapsLayer

  • All Implemented Interfaces:
    java.io.Serializable, java.lang.Iterable<Neuron>


    public class InputMapsLayer
    extends FeatureMapsLayer
    Input layer for convolutional networks
    See Also:
    Serialized Form
    • Field Detail

      • DEFAULT_NEURON_PROP

        public static final NeuronProperties DEFAULT_NEURON_PROP
        Default neuron properties for InputMapsLayer is InputNeuron with Linear transfer function
    • Constructor Detail

      • InputMapsLayer

        public InputMapsLayer(Dimension2D mapDimensions,
                              int mapCount)
        Create InputMapsLayer with specified number of maps with specified dimensions
        Parameters:
        mapDimension - dimensions of a single feature map
        mapCount - number of feature maps
    • Method Detail

      • connectMaps

        public void connectMaps(FeatureMapLayer fromMap,
                                FeatureMapLayer toMap)
        Description copied from class: FeatureMapsLayer
        Creates connections between two feature maps. It does nothing here, connectivity patterns are defined by subclasses... Maybe it should be even removed from here or made abstract......
        Specified by:
        connectMaps in class FeatureMapsLayer

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.