<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RNN on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/rnn/</link><description>Recent content in RNN on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 17 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/rnn/index.xml" rel="self" type="application/rss+xml"/><item><title>Chapter 9: The Transformer Architecture &amp;amp; Attention Mechanisms</title><link>https://ai-blog.noorshomelab.dev/ai-ml-career-path-2026/transformer-architecture/</link><pubDate>Sat, 17 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-ml-career-path-2026/transformer-architecture/</guid><description>&lt;h2 id="chapter-9-the-transformer-architecture--attention-mechanisms"&gt;Chapter 9: The Transformer Architecture &amp;amp; Attention Mechanisms&lt;/h2&gt;
&lt;p&gt;Welcome back, future AI engineer! In our journey so far, we&amp;rsquo;ve explored the foundations of deep learning, from simple feed-forward networks to the power of Convolutional Neural Networks (CNNs) for images and Recurrent Neural Networks (RNNs) for sequences. RNNs, especially their variants like LSTMs and GRUs, were groundbreaking for handling sequential data like text or time series. However, they had a major bottleneck: processing data one step at a time, making them slow for very long sequences and struggling with long-range dependencies.&lt;/p&gt;</description></item></channel></rss>