<p>So I'm not sure if we are able to exactly replicate the MSE from the paper, it's partially stochastic right. However, we should make sure, we can replicate the MSE with a small fraction of noise added.</p>

<p>I couldn't test the code but could you make sure that in each fold the network starts with different weights. I think, it starts with the same weights in each fold.</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 or <a href="https://github.com/mlpack/mlpack/issues/414#issuecomment-211418670">view it on GitHub</a><img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFLLBa8R-hnECLoBTVDEHOpVqckYTks5p451_gaJpZM4DnsTV.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-211418670"></link>
  <meta itemprop="name" content="View Issue"></meta>
</div>
<meta itemprop="description" content="View this Issue on GitHub"></meta>
</div>