<?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 Re: sas machine learning in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/sas-machine-learning/m-p/760760#M8838</link>
    <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;That's a strange question.&amp;nbsp;&lt;span class="lia-unicode-emoji" title=":thinking_face:"&gt;🤔&lt;/span&gt;&lt;span class="lia-unicode-emoji" title=":thinking_face:"&gt;🤔&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;What do you mean with '&lt;SPAN&gt;machine level code'? The source code of SAS itself (often&amp;nbsp;&lt;EM&gt;C&lt;/EM&gt;&amp;nbsp;programming&amp;nbsp;language) is not&amp;nbsp;publicly available.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Which machine learning front-end of SAS are you using and what is your SAS version?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;The front-ends (like Enterprise Miner or Visual Data Mining and Machine Learning in Model Studio) are all SAS-code generators and this SAS code can be looked at of course. The training code can be seen, the scoring code, the LOG info, about everything ...&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Also the documentation (&lt;A href="https://documentation.sas.com/" target="_blank"&gt;https://documentation.sas.com/)&lt;/A&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;gives quite exhaustive info on the algorithms and how they were implemented and what they exactly do (including formulas and equations).&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;But what you mention (log transformation, ADAM, logistic regression, tanh function) are well-known things. SAS is not re-inventing them but just implementing them from widely accepted theory.&lt;BR /&gt;Although I agree that things like nonlinear optimization&amp;nbsp;can be implemented in a good and bad way.&lt;BR /&gt;I am inclined to think that SAS implements things / theory in a good way.&lt;BR /&gt;&lt;BR /&gt;Let us know what you are exactly after.&lt;BR /&gt;&lt;BR /&gt;Koen&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Tue, 10 Aug 2021 21:34:37 GMT</pubDate>
    <dc:creator>sbxkoenk</dc:creator>
    <dc:date>2021-08-10T21:34:37Z</dc:date>
    <item>
      <title>sas machine learning</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/sas-machine-learning/m-p/760579#M8836</link>
      <description>&lt;P&gt;can i get the machine level code or backend code for log transformation, adam, logistic regression, tanh function etc&lt;/P&gt;</description>
      <pubDate>Tue, 10 Aug 2021 11:09:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/sas-machine-learning/m-p/760579#M8836</guid>
      <dc:creator>aftab1</dc:creator>
      <dc:date>2021-08-10T11:09:34Z</dc:date>
    </item>
    <item>
      <title>Re: sas machine learning</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/sas-machine-learning/m-p/760760#M8838</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;That's a strange question.&amp;nbsp;&lt;span class="lia-unicode-emoji" title=":thinking_face:"&gt;🤔&lt;/span&gt;&lt;span class="lia-unicode-emoji" title=":thinking_face:"&gt;🤔&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;What do you mean with '&lt;SPAN&gt;machine level code'? The source code of SAS itself (often&amp;nbsp;&lt;EM&gt;C&lt;/EM&gt;&amp;nbsp;programming&amp;nbsp;language) is not&amp;nbsp;publicly available.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Which machine learning front-end of SAS are you using and what is your SAS version?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;The front-ends (like Enterprise Miner or Visual Data Mining and Machine Learning in Model Studio) are all SAS-code generators and this SAS code can be looked at of course. The training code can be seen, the scoring code, the LOG info, about everything ...&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Also the documentation (&lt;A href="https://documentation.sas.com/" target="_blank"&gt;https://documentation.sas.com/)&lt;/A&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;gives quite exhaustive info on the algorithms and how they were implemented and what they exactly do (including formulas and equations).&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;But what you mention (log transformation, ADAM, logistic regression, tanh function) are well-known things. SAS is not re-inventing them but just implementing them from widely accepted theory.&lt;BR /&gt;Although I agree that things like nonlinear optimization&amp;nbsp;can be implemented in a good and bad way.&lt;BR /&gt;I am inclined to think that SAS implements things / theory in a good way.&lt;BR /&gt;&lt;BR /&gt;Let us know what you are exactly after.&lt;BR /&gt;&lt;BR /&gt;Koen&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Tue, 10 Aug 2021 21:34:37 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/sas-machine-learning/m-p/760760#M8838</guid>
      <dc:creator>sbxkoenk</dc:creator>
      <dc:date>2021-08-10T21:34:37Z</dc:date>
    </item>
  </channel>
</rss>

