kindling-nn-wrappers: kindling-tidymodels wrapper

In kindling: Higher-Level Interface of 'torch' Package to Auto-Train Neural Networks

kindling-tidymodels wrapper

Description

kindling-tidymodels wrapper

Basemodels-tidymodels wrappers

Usage

train_nn_wrapper(formula, data, ...)

ffnn_wrapper(formula, data, ...)

rnn_wrapper(formula, data, ...)

Arguments

formula	A formula specifying the model (e.g., y ~ x1 + x2)
data	A data frame containing the training data
...	Additional arguments passed to the underlying training function

Details

This wrapper function is designed to interface with the {tidymodels} ecosystem, particularly for use with tune::tune_grid() and workflows. It handles the conversion of tuning parameters (especially list-column parameters from grid_depth()) into the format expected by train_nn().

These wrapper functions are designed to interface with the {tidymodels} ecosystem, particularly for use with tune::tune_grid() and workflows. They handle the conversion of tuning parameters (especially list-column parameters from grid_depth()) into the format expected by ffnn() and rnn().

Value

train_nn_wrapper() returns an "nn_fit_tab" object. See train_nn() for details.

• ffnn_wrapper() returns an object of class "ffnn_fit" containing the trained feedforward neural network model and metadata. See ffnn() for details.

• rnn_wrapper() returns an object of class "rnn_fit" containing the trained recurrent neural network model and metadata. See rnn() for details.

MLP Wrapper for {tidymodels} interface

Internal wrapper — use mlp_kindling() + fit() instead.

FFNN (MLP) Wrapper for {tidymodels} interface

This is a function to interface into {tidymodels} (do not use this, use kindling::ffnn() instead).

RNN Wrapper for {tidymodels} interface

Internal wrapper — use rnn_kindling() + fit() instead.

kindling documentation built on March 3, 2026, 9:07 a.m.