MambularRegression<T>

Models & Types · AiDotNet.NeuralNetworks.Tabular

Mambular implementation for regression tasks.

Inheritance: MambularBase<T> → MambularRegression<T>

For Beginners

Use Mambular for regression when:

  • You have many features and need efficient processing
  • You want an alternative to transformer-based models
  • Feature order/sequence matters for your task

Example:

How It Works

MambularRegression applies State Space Models (Mamba architecture) to tabular data for predicting continuous values.

Constructors

Constructor Summary
MambularRegression(int numNumericalFeatures, int outputDimension, MambularOptions<T> options) Initializes a new instance of the MambularRegression 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.