plot_diagonal

If the points come from the predictions of an NN and a PM and the line
<code>(plot.line = TRUE)</code> is displayed, in case the method does exhibit
asymptotic behavior, the points should not fall in the line.

Implements a method that builds the coefficients of a polynomial
model that performs almost equivalently as a given neural network
(densely connected). This is achieved using Taylor expansion at the
activation functions. The obtained polynomial coefficients can be used
to explain features (and their interactions) importance in the neural network,
therefore working as a tool for interpretability or eXplainable Artificial
Intelligence (XAI). See Morala et al. 2021 <doi:10.1016/j.neunet.2021.04.036>,
and 2023 <doi:10.1109/TNNLS.2023.3330328>.

Pablo Morala

nn2poly

Neural Network Weights Transformation into Polynomial
Coefficients

Iñaki Ucar

Jose Ignacio Diez

plot_diagonal function

<dl><dt>x_axis</dt>
<dd>Values to plot in the <code>x</code> axis.</dd>
<dt>y_axis</dt>
<dd>Values to plot in the <code>y</code> axis.</dd>
<dt>xlab</dt>
<dd>Lab of the <code>x</code> axis</dd>
<dt>ylab</dt>
<dd>Lab of the <code>y</code> axis.</dd>
<dt>title</dt>
<dd>Title of the plot.</dd>
<dt>plot.line</dt>
<dd>If a red line with <code>slope = 1</code> and <code>intercept = 0</code> should
be plotted.</dd></dl>

Arguments

Plots a comparison between two sets of points. — plot_diagonal

<dl>

<dt>x_axis</dt>
<dd>Values to plot in the <code>x</code> axis.</dd>


<dt>y_axis</dt>
<dd>Values to plot in the <code>y</code> axis.</dd>


<dt>xlab</dt>
<dd>Lab of the <code>x</code> axis</dd>


<dt>ylab</dt>
<dd>Lab of the <code>y</code> axis.</dd>


<dt>title</dt>
<dd>Title of the plot.</dd>


<dt>plot.line</dt>
<dd>If a red line with <code>slope = 1</code> and <code>intercept = 0</code> should
be plotted.</dd>

</dl>

plot_diagonal: Plots a comparison between two sets of points.

Description

Usage

Value

Arguments