MLP

NeuroTabModels.Models.MLP.MLPConfig Type

MLPConfig(; kwargs...)

Configuration for a multi-layer perceptron backbone.

Arguments

• act::Symbol: Activation — :relu, :gelu, :sigmoid, or :tanh (default :relu).

• hidden_size::Int: Hidden dimension (default 64).

• stack_size::Int: Number of hidden blocks (default 1).

• dropout::Float64: Dropout rate between blocks (default 0.0).

• MLE_tree_split::Bool: Split output head for Gaussian MLE (default false).

source

NeuroTabModels.Models.MLP.MLPConfig Method

(config::MLPConfig)(; nfeats, outsize)

Build a Lux.Chain from config.

Arguments

• nfeats::Int: Number of input features.

• outsize::Int: Number of output units.

Returns

A Lux.Chain of Dense → BatchNorm → Dense blocks with optional dropout.

source