<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>DSWoK — Data Science Well of Knowledge</title>
      <link>https://dswok.com</link>
      <description>Last 10 notes on DSWoK — Data Science Well of Knowledge</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>Attention</title>
    <link>https://dswok.com/General-DL/Attention</link>
    <guid>https://dswok.com/General-DL/Attention</guid>
    <description><![CDATA[ The original paper Attention is a mechanism that lets neural networks focus on specific parts of an input sequence. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Contrastive Language-Image Pre-training</title>
    <link>https://dswok.com/General-DL/Contrastive-Language-Image-Pre-training</link>
    <guid>https://dswok.com/General-DL/Contrastive-Language-Image-Pre-training</guid>
    <description><![CDATA[ CLIP (Contrastive Language-Image Pre-training) is a neural net model developed by OpenAI that efficiently learns visual concepts from natural language supervision. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Deep &amp; Cross Network</title>
    <link>https://dswok.com/General-DL/Deep--and--Cross-Network</link>
    <guid>https://dswok.com/General-DL/Deep--and--Cross-Network</guid>
    <description><![CDATA[ Deep &amp; Cross Network (DCN) is a neural network architecture developed by Google that combines a cross network with a deep network to efficiently learn explicit and implicit feature interactions. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Deep Learning Recommendation Model</title>
    <link>https://dswok.com/General-DL/Deep-Learning-Recommendation-Model</link>
    <guid>https://dswok.com/General-DL/Deep-Learning-Recommendation-Model</guid>
    <description><![CDATA[ Deep Learning Recommendation Model is a neural network architecture developed by Facebook to handle large-scale recommendation tasks efficiently. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>LoRA</title>
    <link>https://dswok.com/General-DL/LoRA</link>
    <guid>https://dswok.com/General-DL/LoRA</guid>
    <description><![CDATA[ LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique that allows to adapt large pre-trained models to specific tasks while minimizing computational resources. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Neural Collaborative Filtering</title>
    <link>https://dswok.com/General-DL/Neural-Collaborative-Filtering</link>
    <guid>https://dswok.com/General-DL/Neural-Collaborative-Filtering</guid>
    <description><![CDATA[ Neural Collaborative Filtering (NCF) is a deep learning approach to collaborative filtering for recommendation systems that aims to learn the complex user-item interaction function using neural networks. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Two-tower</title>
    <link>https://dswok.com/General-DL/Two-tower</link>
    <guid>https://dswok.com/General-DL/Two-tower</guid>
    <description><![CDATA[ Two-tower architecture is a neural network approach used in recommendation systems for candidate generation and retrieval. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Wide &amp; Deep Learning</title>
    <link>https://dswok.com/General-DL/Wide--and--Deep-Learning</link>
    <guid>https://dswok.com/General-DL/Wide--and--Deep-Learning</guid>
    <description><![CDATA[ Wide &amp; Deep Learning is a joint model architecture developed by Google for recommendation systems and search ranking. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>logQ correction</title>
    <link>https://dswok.com/General-DL/logQ-correction</link>
    <guid>https://dswok.com/General-DL/logQ-correction</guid>
    <description><![CDATA[ LogQ correction is a bias correction technique used in recommendation systems to account for non-uniform sampling during training. ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item><item>
    <title>Bias-Variance Trade-off</title>
    <link>https://dswok.com/General-ML/Bias-Variance-Trade-off</link>
    <guid>https://dswok.com/General-ML/Bias-Variance-Trade-off</guid>
    <description><![CDATA[ The bias-variance trade-off is a fundamental concept in machine learning that describes the balance between a model’s ability to fit the training data (low bias) and its ability to generalize to new, unseen data (low variance). ]]></description>
    <pubDate>Sat, 11 Apr 2026 17:18:49 GMT</pubDate>
  </item>
    </channel>
  </rss>