Interface FeedForwardParameters

All Superinterfaces:
Parameters, Serializable
All Known Implementing Classes:
FMParameters, LinearParameters

public interface FeedForwardParameters extends Parameters
A Parameters for models which make a single prediction like logistic regressions and neural networks.
  • Method Details

    • predict

      DenseVector predict(SGDVector example)
      Generates an un-normalized prediction by feeding the features through the parameters.
      Parameters:
      example - The features.
      Returns:
      The prediction.
    • gradients

      Tensor[] gradients(com.oracle.labs.mlrg.olcut.util.Pair<Double,SGDVector> score, SGDVector features)
      Generates the parameter gradients given the loss, output gradient and input features.
      Parameters:
      score - The loss and gradient.
      features - The input features.
      Returns:
      The parameter gradient array.
    • copy

      Returns a copy of the parameters.
      Returns:
      A copy of the model parameters.