early_stop

<code>early_stop()</code> is a helper function to be supplied on <code>early_stopping</code> arguments.

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

early_stop function

<dl><dt>patience</dt>
<dd>Integer. Epochs to wait after last improvement. Default <code>5</code>.</dd>
<dt>min_delta</dt>
<dd>Numeric. Minimum improvement to qualify as better. Default <code>1e-4</code>.</dd>
<dt>restore_best_weights</dt>
<dd>Logical. Restore weights from best epoch. Default <code>TRUE</code>.</dd>
<dt>monitor</dt>
<dd>Character. Metric to monitor. One of <code>"val_loss"</code> (default) or <code>"train_loss"</code>.</dd></dl>

Arguments

Early Stopping Specification — early_stop

<dl>

<dt>patience</dt>
<dd>Integer. Epochs to wait after last improvement. Default <code>5</code>.</dd>


<dt>min_delta</dt>
<dd>Numeric. Minimum improvement to qualify as better. Default <code>1e-4</code>.</dd>


<dt>restore_best_weights</dt>
<dd>Logical. Restore weights from best epoch. Default <code>TRUE</code>.</dd>


<dt>monitor</dt>
<dd>Character. Metric to monitor. One of <code>"val_loss"</code> (default) or <code>"train_loss"</code>.</dd>

</dl>

early_stop: Early Stopping Specification

Description

Usage

Value

Arguments