SAINTRegression<T>

Models & Types · AiDotNet.NeuralNetworks.Tabular

SAINT implementation for regression tasks.

Inheritance: SAINTBase<T> → SAINTRegression<T>

For Beginners

Use SAINT for regression when:

  • You have tabular data with mixed numerical and categorical features
  • You believe similar samples in your data share useful patterns
  • You want state-of-the-art performance on tabular regression

Example:

How It Works

SAINTRegression applies both column attention (over features) and row attention (over samples in a batch) for predicting continuous values on tabular data.

Constructors

Constructor Summary
SAINTRegression(int numNumericalFeatures, int outputDimension, SAINTOptions<T> options) Initializes a new instance of the SAINTRegression class.

Properties

Property Summary
int OutputDimension { get; } Gets the output dimension.

Methods

Method Summary
T ComputeMAELoss(Tensor<T> predictions, Tensor<T> targets) Computes the Mean Absolute Error loss.
T ComputeMSELoss(Tensor<T> predictions, Tensor<T> targets) Computes the Mean Squared Error loss.
T ComputeR2Score(Tensor<T> numericalFeatures, Tensor<T> targets, Matrix<int> categoricalIndices) Computes the R² score (coefficient of determination).
T ComputeRMSE(Tensor<T> numericalFeatures, Tensor<T> targets, Matrix<int> categoricalIndices) Computes the Root Mean Squared Error.
T TrainStep(Tensor<T> numericalFeatures, Tensor<T> targets, T learningRate, Matrix<int> categoricalIndices) Performs a single training step.
Tensor<T> Forward(Tensor<T> numericalFeatures, Matrix<int> categoricalIndices) Performs the forward pass to get predictions.
Tensor<T> Predict(Tensor<T> numericalFeatures, Matrix<int> categoricalIndices) Makes predictions (alias for Forward).
void ResetState() Resets internal state.
void UpdateParameters(T learningRate) Updates all parameters.