<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Morphogenesis on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/morphogenesis/</link>
    <description>Recent content in Morphogenesis on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 10 Aug 2026 20:35:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/morphogenesis/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Cellular Automata From First Principles 39: Grow a Target From One Seed</title>
      <link>http://programmer.ie/post/cellular-automata-from-first-principles-39/</link>
      <pubDate>Mon, 10 Aug 2026 20:35:00 +0100</pubDate>
      <guid>http://programmer.ie/post/cellular-automata-from-first-principles-39/</guid>
      <description>&lt;h1 id=&#34;cellular-automata-from-first-principles-39-grow-a-target-from-one-seed&#34;&gt;Cellular Automata From First Principles 39: Grow a Target From One Seed&lt;/h1&gt;&#xA;&lt;p&gt;Now we can pose the central morphogenesis problem:&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;Start from one cell and learn local rules that construct a target pattern.&lt;/p&gt;&lt;/blockquote&gt;&#xA;&lt;h2 id=&#34;prepare-a-target&#34;&gt;Prepare a target&lt;/h2&gt;&#xA;&lt;p&gt;Assume an RGBA image has been loaded into a tensor:&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; style=&#34;color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;&#34;&gt;&lt;code class=&#34;language-python&#34; data-lang=&#34;python&#34;&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;&lt;span style=&#34;color:#75715e&#34;&gt;# shape: [1, 4, H, W], values in [0, 1]&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;target &lt;span style=&#34;color:#f92672&#34;&gt;=&lt;/span&gt; load_target(&lt;span style=&#34;color:#e6db74&#34;&gt;&amp;#34;target.png&amp;#34;&lt;/span&gt;)&lt;span style=&#34;color:#f92672&#34;&gt;.&lt;/span&gt;to(DEVICE)&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;The NCA state contains more channels than the image, so only the visible channels are compared:&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
