activation_hard_sigmoid

The hard sigmoid activation is defined as:<ul>
<li><code>0</code> if <code>if x &lt;= -3</code></li>
<li><code>1</code> if <code>x &gt;= 3</code></li>
<li><code>(x/6) + 0.5</code> if <code>-3 &lt; x &lt; 3</code></li>
</ul>It's a faster, piecewise linear approximation
of the sigmoid activation.

Interface to 'Keras' <https://keras.io>, a high-level neural
networks API. 'Keras' was developed with a focus on enabling fast experimentation,
supports both convolution based networks and recurrent networks (as well as
combinations of the two), and runs seamlessly on both CPU and GPU devices.

Tomasz Kalinowski

keras3

R Interface to 'Keras'

Daniel Falbel

JJ Allaire

François Chollet

Posit Software, PBC 

Google 

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

activation_hard_sigmoid function

<dl><dt>x</dt>
<dd>Input tensor.</dd></dl>

Arguments

<ul>
<li><a href="https://en.wikipedia.org/wiki/Hard_sigmoid">Wikipedia "Hard sigmoid"</a></li>
</ul>

Reference

The hard sigmoid activation is defined as:<ul>
<li><code>0</code> if <code>if x &lt;= -3</code></li>
<li><code>1</code> if <code>x &gt;= 3</code></li>
<li><code>(x/6) + 0.5</code> if <code>-3 &lt; x &lt; 3</code></li>
</ul>

It's a faster, piecewise linear approximation
of the sigmoid activation.

Hard sigmoid activation function. — activation_hard_sigmoid

<dl>

<dt>x</dt>
<dd>Input tensor.</dd>

</dl>

<ul>
<li><a href='https://en.wikipedia.org/wiki/Hard_sigmoid'>Wikipedia "Hard sigmoid"</a></li>
</ul>

activation_hard_sigmoid: Hard sigmoid activation function.

Description

Usage

Value

Arguments

Reference

See Also