<ol>
<li>It should be the same dataset. And yes you have to split the last dimension from the training. </li>
<li>Take a look at the constructor of the FNN class:</li>
</ol>
<pre><code>FFN(LayerType &&network,
OutputType &&outputLayer,
InitializationRuleType initializeRule = InitializationRuleType(),
PerformanceFunction performanceFunction = PerformanceFunction());
</code></pre>
<p>The third parameter it the object used to initialize the weights. So in your test you should use that parameter, something like this should work:</p>
<pre><code>KathirvalavakumarSubavathiInitialization initRule(data, 0.3);
FFN<decltype(modules),
decltype(classOutputLayer),
KathirvalavakumarSubavathiInitialization,
PerformanceFunctionType> net(modules, classOutputLayer, initRule);
</code></pre>
<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">—<br>Reply to this email directly or <a href="https://github.com/mlpack/mlpack/issues/414#issuecomment-195957988">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFJP7oLMmCiRFaf41g0fCxZw2a8-aks5ptBGHgaJpZM4DnsTV.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/issues/414#issuecomment-195957988"></link>
<meta itemprop="name" content="View Issue"></meta>
</div>
<meta itemprop="description" content="View this Issue on GitHub"></meta>
</div>