AutoIntRegression<T>
Models & Types · AiDotNet.NeuralNetworks.Tabular
AutoInt implementation for regression tasks.
Inheritance: AutoIntBase<T> → AutoIntRegression<T>
For Beginners
Use AutoInt for regression when:
- Feature interactions matter for prediction
- You don’t want to manually engineer feature crosses
- You want interpretable interaction patterns
Example:
How It Works
AutoIntRegression uses multi-head self-attention to automatically learn feature interactions for regression on tabular data.
Constructors
| Constructor | Summary |
|---|---|
AutoIntRegression(int numNumericalFeatures, int outputDimension, AutoIntOptions<T> options) |
Initializes a new instance of the AutoIntRegression 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 by running a forward pass on the given features. |
T ComputeR2Score(Tensor<T> predictions, Tensor<T> targets) |
Computes the R² score (coefficient of determination) from precomputed predictions. |
T ComputeRMSE(Tensor<T> numericalFeatures, Tensor<T> targets, Matrix<int> categoricalIndices) |
Computes the Root Mean Squared Error by running a forward pass on the given features. |
T ComputeRMSE(Tensor<T> predictions, Tensor<T> targets) |
Computes the Root Mean Squared Error from precomputed predictions. |
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 without retaining activations for a backward pass. |
void ResetState() |
Resets internal state. |
void UpdateParameters(T learningRate) |
Updates all parameters. |