<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>Brain Online</title>
      <link>https://brain.maximilianherrmann.com</link>
      <description>Letzte 10 Seiten on Brain Online</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>Regularizers</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Regularizers</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Regularizers</guid>
    <description><![CDATA[ Regularizers Regularization = anything that constrains a model to fight overfitting — it trades a little more bias for a lot less variance (see Bias-Variance Tradeoff). ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:56 GMT</pubDate>
  </item><item>
    <title>Q-Function</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Q-Function</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Q-Function</guid>
    <description><![CDATA[ Q-Function methods-of-ai Difference between reward and Q-Value In reinforcement learning, the concepts of q-value and reward are fundamental but serve different purposes: Reward: The reward is an immediate feedback signal received by the agent after taking an action in a particular state. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>Perceptron</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Perceptron</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Perceptron</guid>
    <description><![CDATA[ Perceptron chatbot methods-of-ai Basics of the Perceptron The perceptron is a simple neural network that serves as a foundational model in neuroinformatics. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>Information Gain</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Information-Gain</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/611-%F0%9F%93%A0Machine-Learning/Information-Gain</guid>
    <description><![CDATA[ Information Gain Information gain aims to reduce entropy — it measures how much knowing the value of an attribute A reduces our uncertainty about the class label of a set S. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>worked-examples_lookahead_29-05-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/worked-examples_lookahead_29-05-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/worked-examples_lookahead_29-05-26</guid>
    <description><![CDATA[ ai-generated methods-of-ai exam-prep Companion to quiz_paper-transformers-search_28-05-26 · Q2 — Lookahead. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>worked-example_qk-dotproduct_29-05-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/worked-example_qk-dotproduct_29-05-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/worked-example_qk-dotproduct_29-05-26</guid>
    <description><![CDATA[ ai-generated methods-of-ai exam-prep Companion to quiz_paper-transformers-search_28-05-26 · Q6 (the Qⱼ·Kᵢ dot products) — also underpins Q7 (path-merging). ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>vagueness-uncertainty_30-04-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/vagueness-uncertainty_30-04-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/vagueness-uncertainty_30-04-26</guid>
    <description><![CDATA[ Vagueness &amp; Uncertainty — moved This topic reference has been merged into the atomic note Fuzzy Logic. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>svm_30-04-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/svm_30-04-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/svm_30-04-26</guid>
    <description><![CDATA[ SVMs &amp; Perceptron — moved This topic reference has been merged into the atomic note: → Support Vector Machines The merged note contains everything that was here (core ideas, glossary, hyperplane setup, Lagrangian &amp; KKT, kernel trick, common kernels, soft-margin, perceptron, XOR, formulas, ex... ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>reviews_paper-transformers-search_28-05-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/reviews_paper-transformers-search_28-05-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/reviews_paper-transformers-search_28-05-26</guid>
    <description><![CDATA[ ai-generated methods-of-ai exam-prep The official ICLR 2025 peer reviews of the exam paper. ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item><item>
    <title>references_paper-transformers-search_28-05-26</title>
    <link>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/references_paper-transformers-search_28-05-26</link>
    <guid>https://brain.maximilianherrmann.com/z-%F0%9F%9B%B8Alle-Notizen/Methods-of-AI/references_paper-transformers-search_28-05-26</guid>
    <description><![CDATA[ ai-generated methods-of-ai exam-prep The most important reference papers behind the exam paper — curated for the oral exam (Mon 1 Jun 2026). ]]></description>
    <pubDate>Mon, 15 Jun 2026 14:29:55 GMT</pubDate>
  </item>
    </channel>
  </rss>