<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>journal on Suriya's site</title><link>https://subygan.com/til/</link><description>Recent content in journal on Suriya's site</description><generator>Hugo</generator><language>en</language><copyright>This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.</copyright><item><title>karpathy micrograd</title><link>https://subygan.com/til/08-02-2025/</link><pubDate>Sat, 08 Feb 2025 00:00:00 +0000</pubDate><guid>https://subygan.com/til/08-02-2025/</guid><description>&lt;p>Went through karpathy&amp;rsquo;s incredible micrograd tutorial.&lt;/p>
&lt;p>His explanation and the code was incredibly intuitive.&lt;/p>
&lt;p>Autograd libraries build a network graph of a given equation with each operation being a node and then apply chain rule to find the local gradient. This is useful because it enables you to calculate back propagation easily as well as locally.&lt;/p></description></item></channel></rss>