<?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 SAS Text Mining: Text Cluster Node with PROC NEURAL? in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/SAS-Text-Mining-Text-Cluster-Node-with-PROC-NEURAL/m-p/481855#M9924</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'm trying to classify several text documents into a binary target using the SAS Text Miner.&lt;/P&gt;&lt;P&gt;I used the Data Partition, Text Parsing and Text Filtering Node to clean up the text data.&lt;/P&gt;&lt;P&gt;For preprocessing, I found out that the text cluster with a neural net gives me the best predictions. However I want to "boost" predictive power using proc NEURAL. According&amp;nbsp;to my understanding, the neural net node only uses 1 layer with max 64 nodes but I want to make the net "deep" with more layers which I could setup using proc NEURAL.&lt;/P&gt;&lt;P&gt;Is it therefore somehow&amp;nbsp;possible using a CNN or even a RNN using Enterprise Miner software?&lt;/P&gt;&lt;P&gt;If not, is it possible to test the SAS Visual Analytics software on a local machine which supports these algorithms?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;KS&lt;/P&gt;</description>
    <pubDate>Fri, 27 Jul 2018 13:30:53 GMT</pubDate>
    <dc:creator>fuhgidabowit</dc:creator>
    <dc:date>2018-07-27T13:30:53Z</dc:date>
    <item>
      <title>SAS Text Mining: Text Cluster Node with PROC NEURAL?</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/SAS-Text-Mining-Text-Cluster-Node-with-PROC-NEURAL/m-p/481855#M9924</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'm trying to classify several text documents into a binary target using the SAS Text Miner.&lt;/P&gt;&lt;P&gt;I used the Data Partition, Text Parsing and Text Filtering Node to clean up the text data.&lt;/P&gt;&lt;P&gt;For preprocessing, I found out that the text cluster with a neural net gives me the best predictions. However I want to "boost" predictive power using proc NEURAL. According&amp;nbsp;to my understanding, the neural net node only uses 1 layer with max 64 nodes but I want to make the net "deep" with more layers which I could setup using proc NEURAL.&lt;/P&gt;&lt;P&gt;Is it therefore somehow&amp;nbsp;possible using a CNN or even a RNN using Enterprise Miner software?&lt;/P&gt;&lt;P&gt;If not, is it possible to test the SAS Visual Analytics software on a local machine which supports these algorithms?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;KS&lt;/P&gt;</description>
      <pubDate>Fri, 27 Jul 2018 13:30:53 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/SAS-Text-Mining-Text-Cluster-Node-with-PROC-NEURAL/m-p/481855#M9924</guid>
      <dc:creator>fuhgidabowit</dc:creator>
      <dc:date>2018-07-27T13:30:53Z</dc:date>
    </item>
    <item>
      <title>Re: SAS Text Mining: Text Cluster Node with PROC NEURAL?</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/SAS-Text-Mining-Text-Cluster-Node-with-PROC-NEURAL/m-p/488301#M9925</link>
      <description>&lt;P&gt;Hi KS,&lt;/P&gt;
&lt;P&gt;No the cnn and rnn actions are not available in&amp;nbsp; Enterprise Miner, but&amp;nbsp; a multi-layer network&amp;nbsp;should be available. Did you click on the&amp;nbsp;"..."&amp;nbsp; button to the right of the "Network" property. I believe there is a setting for&amp;nbsp;number of hidden layers there.&lt;/P&gt;
&lt;P&gt;Russ&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 20 Aug 2018 18:07:41 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/SAS-Text-Mining-Text-Cluster-Node-with-PROC-NEURAL/m-p/488301#M9925</guid>
      <dc:creator>RussAlbright</dc:creator>
      <dc:date>2018-08-20T18:07:41Z</dc:date>
    </item>
  </channel>
</rss>

