Interface CovarianceFunction

All Known Implementing Classes:
CovLINard, CovLINone, CovNNone, CovNNoneNoise, CovNoise, CovSEard, CovSEiso, CovSum

public interface CovarianceFunction
  • Method Summary

    Modifier and Type
    Method
    Description
    Jama.Matrix
    compute(Jama.Matrix loghyper, Jama.Matrix X)
    Compute covariance matrix of a dataset X
    Jama.Matrix[]
    compute(Jama.Matrix loghyper, Jama.Matrix X, Jama.Matrix Xstar)
    Compute compute test set covariances
    Jama.Matrix
    computeDerivatives(Jama.Matrix loghyper, Jama.Matrix X, int index)
    Coompute the derivatives of this CovarianceFunction with respect to the hyperparameter with index idx
    int
    Returns the number of hyperparameters of thisCovarianceFunction
  • Method Details

    • numParameters

      int numParameters()
      Returns the number of hyperparameters of thisCovarianceFunction
      Returns:
      number of hyperparameters
    • compute

      Jama.Matrix compute(Jama.Matrix loghyper, Jama.Matrix X)
      Compute covariance matrix of a dataset X
      Parameters:
      loghyper - column Matrix of hyperparameters
      X - input dataset
      Returns:
      K covariance Matrix
    • compute

      Jama.Matrix[] compute(Jama.Matrix loghyper, Jama.Matrix X, Jama.Matrix Xstar)
      Compute compute test set covariances
      Parameters:
      loghyper - column Matrix of hyperparameters
      X - input dataset
      Xstar - test set
      Returns:
      [K(Xstar, Xstar) K(X,Xstar)]
    • computeDerivatives

      Jama.Matrix computeDerivatives(Jama.Matrix loghyper, Jama.Matrix X, int index)
      Coompute the derivatives of this CovarianceFunction with respect to the hyperparameter with index idx
      Parameters:
      loghyper - hyperparameters
      X - input dataset
      index - hyperparameter index
      Returns:
      Matrix of derivatives