<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[RSS Feed]]></title><description><![CDATA[RSS Feed]]></description><link>https://ecency.com</link><image><url>https://ecency.com/logo512.png</url><title>RSS Feed</title><link>https://ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Wed, 19 Aug 2026 03:30:46 GMT</lastBuildDate><atom:link href="https://ecency.com/@alberduris/rss" rel="self" type="application/rss+xml"/><item><title><![CDATA[What happens when you apply Dropout to a bad initialized Deep Neural Network]]></title><description><![CDATA[Introduction: This is a post that explains a problem that I found during the development of Deep Neural Network (with Tensorflow) in order to do multi-label classification and the applicaton of the popular]]></description><link>https://ecency.com/@alberduris/what-happens-when-you-apply-dropout-to-a-bad-initialized-deep-neural-network</link><guid isPermaLink="true">https://ecency.com/@alberduris/what-happens-when-you-apply-dropout-to-a-bad-initialized-deep-neural-network</guid><category><![CDATA[tensorflow]]></category><dc:creator><![CDATA[alberduris]]></dc:creator><pubDate>Sat, 24 Mar 2018 14:15:15 GMT</pubDate><enclosure url="https://i.ecency.com/p/62PdCouTvNPDuXRaduVYiCb9hxbZWDcAb1acVYBWN5iXusz3hN5auNM3pAyzjVbS7EYHdcnGPWnyWhQnvMHKz32CzKKNDpgpD6BhRruMwyqhH7B?format=match&amp;mode=fit" length="0" type="false"/></item></channel></rss>