<?xml version='1.0' encoding='utf-8' ?>

<rss version='2.0' xmlns:lj='http://www.livejournal.org/rss/lj/1.0/' xmlns:atom10='http://www.w3.org/2005/Atom'>
<channel>
  <title>Anhinga anhinga playground</title>
  <link>https://anhinga-drafts.dreamwidth.org/</link>
  <description>Anhinga anhinga playground - Dreamwidth Studios</description>
  <lastBuildDate>Fri, 10 Jun 2022 02:34:58 GMT</lastBuildDate>
  <generator>LiveJournal / Dreamwidth Studios</generator>
  <lj:journal>anhinga_drafts</lj:journal>
  <lj:journaltype>personal</lj:journaltype>
  <image>
    <url>https://v2.dreamwidth.org/11549496/3235199</url>
    <title>Anhinga anhinga playground</title>
    <link>https://anhinga-drafts.dreamwidth.org/</link>
    <width>92</width>
    <height>91</height>
  </image>

<item>
  <guid isPermaLink='true'>https://anhinga-drafts.dreamwidth.org/30380.html</guid>
  <pubDate>Fri, 10 Jun 2022 02:34:58 GMT</pubDate>
  <title>Two years later/два года спустя</title>
  <link>https://anhinga-drafts.dreamwidth.org/30380.html</link>
  <description>Two years since my last post in this journal, and two years since the revolutionary events of the first half of 2020.&lt;br /&gt;&lt;br /&gt;* The start of the major pandemic and the dynamics of the collective social response to that, the resulting impact was comparable to a soft version of the third World War (which is now gradually becoming less soft and more acute, especially this year).&lt;br /&gt;&lt;br /&gt;* The GPT-3 revolution marking the transition from AI 2.0 (Deep Learning) to AI 3.0 (learning from a single or few examples, more and more competent program synthesis from linguistic clues, competent fast computational protein folding, &quot;foundation models&quot; based on Transformers or sometimes on hybrid models using artificial attention, etc).&lt;br /&gt;&lt;br /&gt;The turbulence and the pace of change are only increasing. Very difficult and very interesting times are likely to be ahead of us this year and further down the road.&lt;br /&gt;&lt;br /&gt;My main online platforms are still the dreamwidth and twitter accounts mentioned in the previous post.&lt;br /&gt;&lt;br /&gt;&lt;img src=&quot;https://www.dreamwidth.org/tools/commentcount?user=anhinga_drafts&amp;ditemid=30380&quot; width=&quot;30&quot; height=&quot;12&quot; alt=&quot;comment count unavailable&quot; style=&quot;vertical-align: middle;&quot;/&gt; comments</description>
  <comments>https://anhinga-drafts.dreamwidth.org/30380.html</comments>
  <lj:security>public</lj:security>
  <lj:reply-count>2</lj:reply-count>
</item>
<item>
  <guid isPermaLink='true'>https://anhinga-drafts.dreamwidth.org/30161.html</guid>
  <pubDate>Wed, 08 Jul 2020 21:26:11 GMT</pubDate>
  <title>dmm.dreamwidth.org; twitter.com/ComputingByArts</title>
  <link>https://anhinga-drafts.dreamwidth.org/30161.html</link>
  <description>The main place of my online activity for the last year:&lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;https://dmm.dreamwidth.org/&quot;&gt;https://dmm.dreamwidth.org/&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;The main place of my online activity for the last couple of months:&lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;https://twitter.com/ComputingByArts&quot;&gt;https://twitter.com/ComputingByArts&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;&lt;img src=&quot;https://www.dreamwidth.org/tools/commentcount?user=anhinga_drafts&amp;ditemid=30161&quot; width=&quot;30&quot; height=&quot;12&quot; alt=&quot;comment count unavailable&quot; style=&quot;vertical-align: middle;&quot;/&gt; comments</description>
  <comments>https://anhinga-drafts.dreamwidth.org/30161.html</comments>
  <lj:security>public</lj:security>
  <lj:reply-count>0</lj:reply-count>
</item>
<item>
  <guid isPermaLink='true'>https://anhinga-drafts.dreamwidth.org/29924.html</guid>
  <pubDate>Sun, 10 Mar 2019 17:08:28 GMT</pubDate>
  <title>Regularization in intrinsically sparse networks</title>
  <link>https://anhinga-drafts.dreamwidth.org/29924.html</link>
  <description>My study (with a set of computational experiments) on the role of regularization in learning the network topology in a relatively novel neuroevolutionary scheme for intrinsically sparse networks:&lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;https://github.com/anhinga/synapses/blob/master/regularization.md&quot;&gt;https://github.com/anhinga/synapses/blob/master/regularization.md&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;&lt;span class=&quot;cut-wrapper&quot;&gt;&lt;span style=&quot;display: none;&quot; id=&quot;span-cuttag___1&quot; class=&quot;cuttag&quot;&gt;&lt;/span&gt;&lt;b class=&quot;cut-open&quot;&gt;(&amp;nbsp;&lt;/b&gt;&lt;b class=&quot;cut-text&quot;&gt;&lt;a href=&quot;https://anhinga-drafts.dreamwidth.org/29924.html#cutid1&quot;&gt;a shorter description here&lt;/a&gt;&lt;/b&gt;&lt;b class=&quot;cut-close&quot;&gt;&amp;nbsp;)&lt;/b&gt;&lt;/span&gt;&lt;div style=&quot;display: none;&quot; id=&quot;div-cuttag___1&quot; aria-live=&quot;assertive&quot;&gt;&lt;/div&gt;&lt;br /&gt;&lt;br /&gt;Crosspost: &lt;a href=&quot;https://anhinga-drafts.livejournal.com/30356.html&quot;&gt;https://anhinga-drafts.livejournal.com/30356.html&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;&lt;img src=&quot;https://www.dreamwidth.org/tools/commentcount?user=anhinga_drafts&amp;ditemid=29924&quot; width=&quot;30&quot; height=&quot;12&quot; alt=&quot;comment count unavailable&quot; style=&quot;vertical-align: middle;&quot;/&gt; comments</description>
  <comments>https://anhinga-drafts.dreamwidth.org/29924.html</comments>
  <lj:security>public</lj:security>
  <lj:reply-count>0</lj:reply-count>
</item>
</channel>
</rss>
