<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Question about the HP Neural Network Node in SAS Academy for Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552658#M300</link>
    <description>&lt;P&gt;In Module 4, chapter 6, the subsection that presents parallel processing the task of building/training a neural network model, the instructor explains information panel for the HPNN node. &amp;nbsp;Within this panel, there are two areas that allow the user to modify the algorithm.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;In the section titled “Network Options”, the user can specify the architecture and the number of hidden layers. &amp;nbsp;In the example, the instructor used the setting of “architecture” equal to “One Layer” and the “number of hidden layers” equal to 3.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;My question is “Doesn’t the ‘One Layer’ setting indicate that there will be ONLY one hidden layer?” &amp;nbsp;If the answer is yes, then does SAS disregard hidden layers set to 3?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Sat, 20 Apr 2019 22:05:47 GMT</pubDate>
    <dc:creator>WWD</dc:creator>
    <dc:date>2019-04-20T22:05:47Z</dc:date>
    <item>
      <title>Question about the HP Neural Network Node</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552658#M300</link>
      <description>&lt;P&gt;In Module 4, chapter 6, the subsection that presents parallel processing the task of building/training a neural network model, the instructor explains information panel for the HPNN node. &amp;nbsp;Within this panel, there are two areas that allow the user to modify the algorithm.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;In the section titled “Network Options”, the user can specify the architecture and the number of hidden layers. &amp;nbsp;In the example, the instructor used the setting of “architecture” equal to “One Layer” and the “number of hidden layers” equal to 3.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;My question is “Doesn’t the ‘One Layer’ setting indicate that there will be ONLY one hidden layer?” &amp;nbsp;If the answer is yes, then does SAS disregard hidden layers set to 3?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Sat, 20 Apr 2019 22:05:47 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552658#M300</guid>
      <dc:creator>WWD</dc:creator>
      <dc:date>2019-04-20T22:05:47Z</dc:date>
    </item>
    <item>
      <title>Re: Question about the HP Neural Network Node</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552736#M301</link>
      <description>Hi:&lt;BR /&gt;  We've asked the instructors for the course to take a look at your question. Someone will post a response.&lt;BR /&gt;Cynthia</description>
      <pubDate>Mon, 22 Apr 2019 00:01:23 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552736#M301</guid>
      <dc:creator>Cynthia_sas</dc:creator>
      <dc:date>2019-04-22T00:01:23Z</dc:date>
    </item>
    <item>
      <title>Re: Question about the HP Neural Network Node</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552860#M302</link>
      <description>&lt;P&gt;If you look at the property "number of hidden layers" it is shaded in grey.&amp;nbsp; This means that the property is not being used (it is ignored for the current run).&amp;nbsp; The property "architecture" is white so it is being used.&amp;nbsp; The neural network will have one hidden layer due to the active property of "architecture".&amp;nbsp; To activate the "number of hidden layers" property you would need to set "architecture" to "user defined".&amp;nbsp; This would then activate the "number of hidden layers" property (it would turn white) and then its value would be used.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;So keep in mind that for Enterprise Miner, anytime a property is colored in grey, it is ignored.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Hope this helps!&lt;/P&gt;</description>
      <pubDate>Mon, 22 Apr 2019 14:32:17 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/552860#M302</guid>
      <dc:creator>JThompson</dc:creator>
      <dc:date>2019-04-22T14:32:17Z</dc:date>
    </item>
    <item>
      <title>Re: Question about the HP Neural Network Node</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/553936#M303</link>
      <description>&lt;P&gt;Thank you. &amp;nbsp;I’m good to go.&lt;/P&gt;</description>
      <pubDate>Thu, 25 Apr 2019 12:41:42 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Question-about-the-HP-Neural-Network-Node/m-p/553936#M303</guid>
      <dc:creator>WWD</dc:creator>
      <dc:date>2019-04-25T12:41:42Z</dc:date>
    </item>
  </channel>
</rss>

