<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Deep-Learning on Hitesh Pattanayak</title><link>/tags/deep-learning/</link><description>Recent content in Deep-Learning on Hitesh Pattanayak</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 22 Mar 2026 11:43:37 -0700</lastBuildDate><atom:link href="/tags/deep-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>The Evolution: Beyond Transformers</title><link>/posts/the-evolution-beyond-transformers/</link><pubDate>Sun, 22 Mar 2026 11:43:37 -0700</pubDate><guid>/posts/the-evolution-beyond-transformers/</guid><description>A practical walkthrough of how the Transformer architecture evolved from encoder-decoder to decoder-only models, why attention&amp;rsquo;s quadratic scaling became a hard wall, and how Mamba&amp;rsquo;s state space machines are being absorbed into hybrid architectures that dominate production today.</description></item><item><title>The End of the RNN Era &amp; The Query, Key, Value Revolution</title><link>/posts/the-end-of-the-rnn-era-the-query-key-value-revolution/</link><pubDate>Sat, 21 Mar 2026 12:06:03 -0700</pubDate><guid>/posts/the-end-of-the-rnn-era-the-query-key-value-revolution/</guid><description>A practical walkthrough of why RNNs hit a fundamental wall with sequential processing and long-range dependencies, and how the Query-Key-Value attention mechanism solves both problems in one elegant step.</description></item><item><title>Understanding Neural Networks: Weights, Biases, and Activations</title><link>/posts/deep-learning/</link><pubDate>Sat, 12 Oct 2024 00:00:00 +0000</pubDate><guid>/posts/deep-learning/</guid><description>This article breaks down the key mathematical concepts behind neural networks, including weights, biases, and activations, with an example of handwritten digit recognition.</description></item></channel></rss>