<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>Quartz 4</title>
      <link>https://bowen0701.github.io/research-eng</link>
      <description>Last 10 notes on Quartz 4</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>Bowen&#039;s RE Log</title>
    <link>https://bowen0701.github.io/research-eng/</link>
    <guid>https://bowen0701.github.io/research-eng/</guid>
    <description><![CDATA[ Welcome to Bowen’s RE Log Hi, this is Bowen. ]]></description>
    <pubDate>Sat, 16 May 2026 23:46:39 GMT</pubDate>
  </item><item>
    <title>He Initialization</title>
    <link>https://bowen0701.github.io/research-eng/He-Initialization</link>
    <guid>https://bowen0701.github.io/research-eng/He-Initialization</guid>
    <description><![CDATA[ Concept: He Initialization Core Intuition Designed to solve the vanishing/exploding gradient problem in deep networks using ReLU activations. ]]></description>
    <pubDate>Wed, 13 May 2026 00:00:00 GMT</pubDate>
  </item><item>
    <title>Manual Layer</title>
    <link>https://bowen0701.github.io/research-eng/Manual-Layers</link>
    <guid>https://bowen0701.github.io/research-eng/Manual-Layers</guid>
    <description><![CDATA[ Concept: Manual Layer Core Intuition A Linear Layer (or Fully Connected/Dense layer) performs an affine transformation on input data. ]]></description>
    <pubDate>Wed, 13 May 2026 00:00:00 GMT</pubDate>
  </item><item>
    <title>Correspondence Analysis</title>
    <link>https://bowen0701.github.io/research-eng/Correspondence-Analysis</link>
    <guid>https://bowen0701.github.io/research-eng/Correspondence-Analysis</guid>
    <description><![CDATA[ Concept: Correspondence Analysis Core Intuition Correspondence Analysis (CA) is a dimensionality reduction and data visualization technique for contingency tables of counts. ]]></description>
    <pubDate>Thu, 06 Oct 2016 00:00:00 GMT</pubDate>
  </item><item>
    <title>PCA and SVD</title>
    <link>https://bowen0701.github.io/research-eng/PCA-and-SVD</link>
    <guid>https://bowen0701.github.io/research-eng/PCA-and-SVD</guid>
    <description><![CDATA[ Concept: PCA and SVD Core Intuition PCA identifies the most meaningful basis to re-express data by maximizing the signal-to-noise ratio (SNR): \sigma^2_{signal} / \sigma^2_{noise}. ]]></description>
    <pubDate>Wed, 05 Oct 2016 00:00:00 GMT</pubDate>
  </item>
    </channel>
  </rss>