NODERegression<T>
Models & Types · AiDotNet.NeuralNetworks.Tabular
NODE implementation for regression tasks.
Inheritance: NODEBase<T> → NODERegression<T>
For Beginners
Use NODE for regression when you want:
- Interpretable models (see feature importance via GetFeatureImportance())
- Tree-based structure with neural network trainability
- Good performance on tabular data with continuous targets
Example:
How It Works
NODERegression uses an ensemble of differentiable oblivious decision trees for predicting continuous values on tabular data.
Constructors
| Constructor | Summary |
|---|---|
NODERegression(int numFeatures, int outputDimension, NODEOptions<T> options) |
Initializes a new instance of the NODERegression 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> features, Tensor<T> targets) |
Computes the R² score (coefficient of determination). |
T ComputeRMSE(Tensor<T> features, Tensor<T> targets) |
Computes the Root Mean Squared Error. |
T TrainStep(Tensor<T> features, Tensor<T> targets, T learningRate) |
Performs a single training step. |
Tensor<T> Forward(Tensor<T> features) |
Performs the forward pass to get predictions. |
Tensor<T> Predict(Tensor<T> features) |
Makes predictions (alias for Forward). |
void ResetState() |
Resets internal state. |
void UpdateParameters(T learningRate) |
Updates all parameters. |