StandardGaussianProcess<T>

Models & Types · AiDotNet.GaussianProcesses

Implements a standard Gaussian Process regression model for making probabilistic predictions.

Inheritance: ModelBase<T, Matrix<T>, Vector<T>> → GaussianProcessBase<T> → StandardGaussianProcess<T>

Implements: IGeneratedParameterRegistrar<T>

For Beginners

A Gaussian Process is a flexible machine learning method that can make predictions with uncertainty estimates.

Think of it like drawing a line through data points, but instead of just one line, it gives you a range of possible lines with a confidence level for each. This helps you understand not just what the prediction is, but how certain the model is about that prediction.

Gaussian Processes are particularly useful when:

  • You have a small to medium amount of data
  • You need to know how confident the model is in its predictions
  • Your data might have complex patterns that simpler models can’t capture

Unlike many other machine learning methods, Gaussian Processes don’t just learn a fixed set of parameters - they use all training data when making predictions, which allows them to capture complex patterns in your data.

Constructors

Constructor Summary
StandardGaussianProcess(IKernelFunction<T> kernel, MatrixDecompositionType decompositionType, double noiseVariance) Initializes a new instance of the StandardGaussianProcess class.

Methods

Method Summary
ValueTuple<T, T> Predict(Vector<T> x) Makes a prediction for a new data point, returning both the predicted value and its uncertainty.
void Fit(Matrix<T> X, Vector<T> y) Trains the Gaussian Process model on the provided data.
void UpdateKernel(IKernelFunction<T> kernel) Updates the kernel function used by the model and recalculates the kernel matrix if training data exists.