Package ai.libs.jaicore.ml.dyadranking.algorithm

Interface IPLNetDyadRankerConfiguration

    • Nested Class Summary

      • Nested classes/interfaces inherited from interface org.aeonbits.owner.Config

        org.aeonbits.owner.Config.ConverterClass, org.aeonbits.owner.Config.DecryptorClass, org.aeonbits.owner.Config.DefaultValue, org.aeonbits.owner.Config.DisableableFeature, org.aeonbits.owner.Config.DisableFeature, org.aeonbits.owner.Config.EncryptedValue, org.aeonbits.owner.Config.HotReload, org.aeonbits.owner.Config.HotReloadType, org.aeonbits.owner.Config.Key, org.aeonbits.owner.Config.LoadPolicy, org.aeonbits.owner.Config.LoadType, org.aeonbits.owner.Config.PreprocessorClasses, org.aeonbits.owner.Config.Separator, org.aeonbits.owner.Config.Sources, org.aeonbits.owner.Config.TokenizerClass

    • Field Summary

      Fields 
      Modifier and Type Field Description
      static java.lang.String K_ACTIVATION_FUNCTION
      The activation function for the hidden layers.
      static java.lang.String K_EARLY_STOPPING_INTERVAL
      How often (in epochs) the validation error should be checked for early stopping.
      static java.lang.String K_EARLY_STOPPING_PATIENCE
      For how many epochs early stopping should wait until training is stopped if no improvement in the validation error is observed.
      static java.lang.String K_EARLY_STOPPING_RETRAIN
      Whether to retrain on the full training data after early stopping, using the same number of epochs the model was trained for before early stopping occured.
      static java.lang.String K_EARLY_STOPPING_TRAIN_RATIO
      The ratio of data used for training in early stopping. 1 - this ratio is used for testing.
      static java.lang.String K_MAX_EPOCHS
      The maximum number of epochs to be used during training, i.e. how many times the training algorithm should iterate through the entire training data set.
      static java.lang.String K_MINI_BATCH_SIZE
      The size of mini batches used during training.
      static java.lang.String K_PLNET_HIDDEN_NODES
      List of integers describing the architecture of the hidden layers.
      static java.lang.String K_PLNET_LEARNINGRATE
      The learning rate for the gradient updater.
      static java.lang.String K_PLNET_SEED
      The random seed to use.

    • Field Detail

      • K_PLNET_LEARNINGRATE

        static final java.lang.String K_PLNET_LEARNINGRATE
        The learning rate for the gradient updater.
        See Also:
        Constant Field Values

      • K_PLNET_HIDDEN_NODES

        static final java.lang.String K_PLNET_HIDDEN_NODES
        List of integers describing the architecture of the hidden layers. The i-th element represents the number of units in the i-th hidden layer.
        See Also:
        Constant Field Values

      • K_PLNET_SEED

        static final java.lang.String K_PLNET_SEED
        The random seed to use.
        See Also:
        Constant Field Values

      • K_MAX_EPOCHS

        static final java.lang.String K_MAX_EPOCHS
        The maximum number of epochs to be used during training, i.e. how many times the training algorithm should iterate through the entire training data set. Set to 0 for no limit apart from early stopping.
        See Also:
        Constant Field Values

      • K_MINI_BATCH_SIZE

        static final java.lang.String K_MINI_BATCH_SIZE
        The size of mini batches used during training.
        See Also:
        Constant Field Values

      • K_EARLY_STOPPING_INTERVAL

        static final java.lang.String K_EARLY_STOPPING_INTERVAL
        How often (in epochs) the validation error should be checked for early stopping.
        See Also:
        Constant Field Values

      • K_EARLY_STOPPING_PATIENCE

        static final java.lang.String K_EARLY_STOPPING_PATIENCE
        For how many epochs early stopping should wait until training is stopped if no improvement in the validation error is observed.
        See Also:
        Constant Field Values

      • K_EARLY_STOPPING_TRAIN_RATIO

        static final java.lang.String K_EARLY_STOPPING_TRAIN_RATIO
        The ratio of data used for training in early stopping. 1 - this ratio is used for testing.
        See Also:
        Constant Field Values

      • K_EARLY_STOPPING_RETRAIN

        static final java.lang.String K_EARLY_STOPPING_RETRAIN
        Whether to retrain on the full training data after early stopping, using the same number of epochs the model was trained for before early stopping occured.
        See Also:
        Constant Field Values

    • Method Detail

      • plNetLearningRate

        @Key("plnet.learningrate")
@DefaultValue("0.1")
double plNetLearningRate()

      • plNetHiddenNodes

        @Key("plnet.hidden.nodes")
@DefaultValue("8")
java.util.List<java.lang.Integer> plNetHiddenNodes()

      • plNetSeed

        @Key("plnet.seed")
@DefaultValue("42")
int plNetSeed()

      • plNetActivationFunction

        @Key("plnet.hidden.activation.function")
@DefaultValue("SIGMOID")
java.lang.String plNetActivationFunction()

      • plNetMaxEpochs

        @Key("plnet.epochs")
@DefaultValue("25")
int plNetMaxEpochs()

      • plNetMiniBatchSize

        @Key("plnet.minibatch.size")
@DefaultValue("4")
int plNetMiniBatchSize()

      • plNetEarlyStoppingInterval

        @Key("plnet.early.stopping.interval")
@DefaultValue("1")
int plNetEarlyStoppingInterval()

      • plNetEarlyStoppingPatience

        @Key("plnet.early.stopping.patience")
@DefaultValue("10")
int plNetEarlyStoppingPatience()

      • plNetEarlyStoppingTrainRatio

        @Key("plnet.early.stopping.train.ratio")
@DefaultValue("0.8")
double plNetEarlyStoppingTrainRatio()

      • plNetEarlyStoppingRetrain

        @Key("plnet.early.stopping.retrain")
@DefaultValue("true")
boolean plNetEarlyStoppingRetrain()