MambularOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for Mambular (State Space Models for Tabular Data).

Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → FinancialNeuralNetworkOptions → RiskModelOptions<T> → MambularOptions<T>

For Beginners

Mambular treats your features like a sequence:

  • State Space Models: An efficient alternative to transformers
  • Linear complexity: Scales better than attention with many features
  • Selective mechanism: Learns which features to remember/forget

Example:

How It Works

Mambular applies the Mamba (State Space Model) architecture to tabular data, treating features as a sequence and using selective state spaces for processing.

Reference: “Mambular: A Sequential Model for Tabular Deep Learning” (2024)

Constructors

Constructor Summary
MambularOptions()

Properties

Property Summary
IActivationFunction<T> HiddenActivation { get; set; } Gets or sets the hidden layer activation function for the MLP head.
IVectorActivationFunction<T> HiddenVectorActivation { get; set; } Gets or sets the hidden layer vector activation function (alternative to scalar activation).
bool UseBidirectional { get; set; } Gets or sets whether to use bidirectional processing.
double DeltaMax { get; set; } Gets or sets the delta (discretization step) range maximum.
double DeltaMin { get; set; } Gets or sets the delta (discretization step) range minimum.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double InitScale { get; set; } Gets or sets the initialization scale for parameters.
int ConvKernelSize { get; set; } Gets or sets the convolution kernel size.
int EmbeddingDimension { get; set; } Gets or sets the embedding dimension for features.
int ExpansionFactor { get; set; } Gets or sets the expansion factor for the inner dimension.
int InnerDimension { get; } Gets the inner dimension.
int NumLayers { get; set; } Gets or sets the number of Mamba layers.
int StateDimension { get; set; } Gets or sets the state dimension for the SSM.
int[] CategoricalCardinalities { get; set; } Gets or sets the cardinalities of categorical features.
int[] MLPHiddenDimensions { get; set; } Gets or sets the hidden dimensions for the MLP head.