<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Strides on Programmer.ie</title>
    <link>http://programmer.ie/tags/strides/</link>
    <description>Recent content in Strides on Programmer.ie</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 08 Aug 2026 12:45:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/strides/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Tensor: What Is Actually Flowing Through the Loop?</title>
      <link>http://programmer.ie/books/pytorch-from-first-principles/02-chapter/</link>
      <pubDate>Sat, 08 Aug 2026 12:45:00 +0100</pubDate>
      <guid>http://programmer.ie/books/pytorch-from-first-principles/02-chapter/</guid>
      <description>&lt;p&gt;The last program in Chapter 1 trained a two-parameter model on four examples. It worked, and we read it as a story about gradients: predict, measure, differentiate, step. But something in it went unexamined. &lt;code&gt;w&lt;/code&gt; was a single number and &lt;code&gt;x&lt;/code&gt; held four, and &lt;code&gt;w * x + b&lt;/code&gt; produced four predictions without anyone specifying how a scalar and a four-element vector should combine. PyTorch had a rule. We never stated it.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
