<p>In <a href="https://github.com/mlpack/mlpack/pull/686#discussion_r66256595">src/mlpack/methods/ne/genome.hpp</a>:</p>
<pre style='color:#555'>&gt; +
&gt; +      // Loop neurons to calculate neurons&#39; activation.
&gt; +      for (unsigned in j=aNumInput; j&lt;aNeuronGenes.size(); ++j) {
&gt; +        double x = aNeuronGenes[j].aInput;  // TODO: consider bias. Difference?
&gt; +        aNeuronGenes[j].aInput = 0;
&gt; +
&gt; +        double y = 0;
&gt; +        switch (aNeuronGenes[j].Type()) { // TODO: revise the implementation.
&gt; +          case SIGMOID:                   // TODO: more cases.
&gt; +            y = sigmoid(x);
&gt; +            break;
&gt; +          case RELU:
&gt; +            y = relu(x);
&gt; +            break;
&gt; +          default:
&gt; +            y = sigmoid(x);
</pre>
<p><a href="https://github.com/zoq" class="user-mention">@zoq</a> I got you point! Seems it is better to use the existing ANN activation functions.</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/686/files/3c8aa62b951f029b3883e9baef1ea556ef5af2d3#r66256595">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe/AJ4bFBsSXUK7xHCg8l7Bk-jCU5zxUJllks5qJsX8gaJpZM4IwJa6">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFAe2rddm3NFKhEZBkQhuTmi2aUeuks5qJsX8gaJpZM4IwJa6.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
  <link itemprop="url" href="https://github.com/mlpack/mlpack/pull/686/files/3c8aa62b951f029b3883e9baef1ea556ef5af2d3#r66256595"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>