AutoIntClassifier<T>

Models & Types · AiDotNet.NeuralNetworks.Tabular

AutoInt implementation for classification tasks.

Inheritance: AutoIntBase<T> → AutoIntClassifier<T>

For Beginners

Use AutoInt for classification when:

  • Feature interactions matter (e.g., age + product_category)
  • You don’t want to manually engineer feature crosses
  • You want interpretable interaction patterns

Example:

How It Works

AutoIntClassifier uses multi-head self-attention to automatically learn feature interactions for classification on tabular data.

Constructors

Constructor Summary
AutoIntClassifier(int numNumericalFeatures, int numClasses, AutoIntOptions<T> options) Initializes a new instance of the AutoIntClassifier class.

Properties

Property Summary
int NumClasses { get; } Gets the number of output classes.

Methods

Method Summary
T ComputeAccuracy(Tensor<T> numericalFeatures, Vector<int> targets, Matrix<int> categoricalIndices) Computes classification accuracy.
T ComputeCrossEntropyLoss(Tensor<T> probabilities, Vector<int> targets) Computes the cross-entropy loss.
T TrainStep(Tensor<T> numericalFeatures, Vector<int> 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 class logits.
Tensor<T> PredictProbabilities(Tensor<T> numericalFeatures, Matrix<int> categoricalIndices) Predicts class probabilities using softmax.
Vector<int> Predict(Tensor<T> numericalFeatures, Matrix<int> categoricalIndices) Predicts the most likely class for each sample.
void ResetState() Resets internal state.
void UpdateParameters(T learningRate) Updates all parameters.