<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>Notes</title>
      <link>https://pawel002.github.io/notes</link>
      <description>Last 10 notes on Notes</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>You Only Look Once</title>
    <link>https://pawel002.github.io/notes/computer-vision/yolo</link>
    <guid>https://pawel002.github.io/notes/computer-vision/yolo</guid>
    <description><![CDATA[  \newcommand{\loss}{\mathcal{L}} \newcommand{\one}{\mathbf{1}} Introduction to the architecture Before YOLO, models like R-CNN used a two-stage approach: first proposing potential regions where objects might be, and then classifying those regions. ]]></description>
    <pubDate>Fri, 06 Mar 2026 16:51:18 GMT</pubDate>
  </item><item>
    <title>Segmentation</title>
    <link>https://pawel002.github.io/notes/computer-vision/segmentation</link>
    <guid>https://pawel002.github.io/notes/computer-vision/segmentation</guid>
    <description><![CDATA[ Introduction to Segmentation In digital image processing and computer vision, image segmentation is the process of partitioning a digital image into multiple image segments, also known as image regions or image objects (sets of pixels). ]]></description>
    <pubDate>Tue, 03 Mar 2026 22:33:48 GMT</pubDate>
  </item><item>
    <title>Gradient Boosting</title>
    <link>https://pawel002.github.io/notes/machine-learning/gradient-boosting</link>
    <guid>https://pawel002.github.io/notes/machine-learning/gradient-boosting</guid>
    <description><![CDATA[ Gradient boosting is based on combining many weak learners and deriving the final decision from this combined “strong” learner. ]]></description>
    <pubDate>Fri, 20 Feb 2026 19:48:25 GMT</pubDate>
  </item><item>
    <title>Notes</title>
    <link>https://pawel002.github.io/notes/</link>
    <guid>https://pawel002.github.io/notes/</guid>
    <description><![CDATA[ Topics Computer Vision Machine Learning . ]]></description>
    <pubDate>Thu, 19 Feb 2026 14:56:01 GMT</pubDate>
  </item><item>
    <title>Model Optimization</title>
    <link>https://pawel002.github.io/notes/machine-learning/model-optimization</link>
    <guid>https://pawel002.github.io/notes/machine-learning/model-optimization</guid>
    <description><![CDATA[ Quantization Quantizing a model basically reduces the size of the model so it can fit into the machine with less memory. ]]></description>
    <pubDate>Thu, 19 Feb 2026 14:53:26 GMT</pubDate>
  </item><item>
    <title>Introduction to Neural Networks</title>
    <link>https://pawel002.github.io/notes/machine-learning/nn-introduction</link>
    <guid>https://pawel002.github.io/notes/machine-learning/nn-introduction</guid>
    <description><![CDATA[  \newcommand{\loss}{\mathcal{L}} \newcommand{\Dtrain}{\mathcal{D}\_{\text{train}}} \newcommand{\Dval}{\mathcal{D}\_{\text{val}}} \newcommand{\din}{d\_{\text{in}}} \newcommand{\dout}{d\_{\text{out}}} \newcommand{\one}{\mathbf{1}} \newcommand{\pdv}[2]{\frac{\partial #1}{\partial #2}} \newcommand{\R}{\... ]]></description>
    <pubDate>Thu, 19 Feb 2026 14:53:26 GMT</pubDate>
  </item><item>
    <title>Image Recognition</title>
    <link>https://pawel002.github.io/notes/computer-vision/03-recognition</link>
    <guid>https://pawel002.github.io/notes/computer-vision/03-recognition</guid>
    <description><![CDATA[ Instance Recognition Good example of the classic approach is instance recognition, where we are trying to find exemplars of particular class (for example a stop sign). ]]></description>
    <pubDate>Wed, 18 Feb 2026 22:44:21 GMT</pubDate>
  </item><item>
    <title>Introduction to Computer Vision</title>
    <link>https://pawel002.github.io/notes/computer-vision/01-introduction</link>
    <guid>https://pawel002.github.io/notes/computer-vision/01-introduction</guid>
    <description><![CDATA[ The majority of the introductory notes are based on the 2nd edition book called Computer Vision: Algorithms and Applications released by Richard Szeliski in 2022. ]]></description>
    <pubDate>Tue, 17 Feb 2026 23:12:10 GMT</pubDate>
  </item><item>
    <title>Deep Learning</title>
    <link>https://pawel002.github.io/notes/computer-vision/02-deep-learning</link>
    <guid>https://pawel002.github.io/notes/computer-vision/02-deep-learning</guid>
    <description><![CDATA[ Traditional CV techniques were always based on hand-crafted algorithms. ]]></description>
    <pubDate>Tue, 17 Feb 2026 23:12:10 GMT</pubDate>
  </item>
    </channel>
  </rss>