train_nn_wrapper

ffnn_wrapper

rnn_wrapper

kindling-tidymodels wrapper
Basemodels-tidymodels wrappers

internal

Provides a higher-level interface to the 'torch' package for defining,
training, and fine-tuning neural networks, including its depth, powered by code generation.
This package supports few to several architectures, including feedforward (multi-layer perceptron)
and recurrent neural networks (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)),
while also reduces boilerplate 'torch' code while enabling seamless integration with 'torch'. The model methods
to train neural networks from this package also bridges to titanic ML frameworks in R, namely
'tidymodels' ecosystem, which enables the 'parsnip' model specifications, workflows, recipes,
and tuning tools.

Joshua Marie

kindling

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

Antoine Soetewey

train_nn_wrapper function

<dl><dt>formula</dt>
<dd>A formula specifying the model (e.g., <code>y ~ x1 + x2</code>)</dd>
<dt>data</dt>
<dd>A data frame containing the training data</dd>
<dt>...</dt>
<dd>Additional arguments passed to the underlying training function</dd></dl>

Arguments

Internal wrapper — use <code>mlp_kindling()</code> + <code>fit()</code> instead.

MLP Wrapper for <code>{tidymodels}</code> interface

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

FFNN (MLP) Wrapper for <code>{tidymodels}</code> interface

Internal wrapper — use <code>rnn_kindling()</code> + <code>fit()</code> instead.

RNN Wrapper for <code>{tidymodels}</code> interface

kindling-tidymodels wrapper — train_nn_wrapper

<dl>

<dt>formula</dt>
<dd>A formula specifying the model (e.g., <code>y ~ x1 + x2</code>)</dd>


<dt>data</dt>
<dd>A data frame containing the training data</dd>


<dt>...</dt>
<dd>Additional arguments passed to the underlying training function</dd>

</dl>

Internal wrapper — use <code>mlp_kindling()</code> + <code>fit()</code> instead.

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

Internal wrapper — use <code>rnn_kindling()</code> + <code>fit()</code> instead.

train_nn_wrapper: kindling-tidymodels wrapper

Description

Usage

Value

Arguments

MLP Wrapper for <code>{tidymodels}</code> interface

FFNN (MLP) Wrapper for <code>{tidymodels}</code> interface

RNN Wrapper for <code>{tidymodels}</code> interface

Details