Package org.neo4j.gds.ml.gradientdescent

Interface Objective<DATA>

All Known Implementing Classes:
LinearRegressionObjective, LogisticRegressionObjective, MLPClassifierObjective
public interface Objective<DATA>
A training objective that computes a loss over a batch of nodes

  • Method Summary

    Modifier and Type
    Method
    Description
    static org.neo4j.gds.ml.core.functions.Constant<org.neo4j.gds.ml.core.tensor.Matrix>
    batchFeatureMatrix(org.neo4j.gds.ml.core.batch.Batch batch, Features features)
     
    org.neo4j.gds.ml.core.Variable<org.neo4j.gds.ml.core.tensor.Scalar>
    loss(org.neo4j.gds.ml.core.batch.Batch batch, long trainSize)
     
    DATA
    modelData()
    Returns the data, such as weights, needed to store or load the model
    List<org.neo4j.gds.ml.core.functions.Weights<? extends org.neo4j.gds.ml.core.tensor.Tensor<?>>>
    weights()
     

  • Method Details

    • weights

      List<org.neo4j.gds.ml.core.functions.Weights<? extends org.neo4j.gds.ml.core.tensor.Tensor<?>>> weights()

    • loss

      org.neo4j.gds.ml.core.Variable<org.neo4j.gds.ml.core.tensor.Scalar> loss(org.neo4j.gds.ml.core.batch.Batch batch, long trainSize)

    • modelData

      DATA modelData()
      Returns the data, such as weights, needed to store or load the model
      Returns:
      the data

    • batchFeatureMatrix

      static org.neo4j.gds.ml.core.functions.Constant<org.neo4j.gds.ml.core.tensor.Matrix> batchFeatureMatrix(org.neo4j.gds.ml.core.batch.Batch batch, Features features)