feat: 完整中文翻译 maths-cs-ai-compendium（数学·计算机科学·AI 知识大全）

翻译自英文原版 maths-cs-ai-compendium，共 20 章全部完成。第01章向量 | 第02章矩阵 | 第03章微积分第04章统计学 | 第05章概率论 | 第06章机器学习第07章计算语言学 | 第08章计算机视觉 | 第09章音频与语音第10章多模态学习 | 第11章自主系统 | 第12章图神经网络第13章计算与操作系统 | 第14章数据结构与算法第15章生产级软件工程 | 第16章 SIMD与GPU编程第17章 AI推理 | 第18章 ML系统设计第19章应用人工智能 | 第20章前沿人工智能翻译说明： - 所有数学公式 $...$ / $$...$$、代码块、图片引用完整保留 - mkdocs.yml 配置中文导航 + language: zh - README.md 已翻译为中文（兼 docs/index.md） - docs/ 目录包含指向各章文件的 symlink - 约 29,000 行中文内容，排除 .cache/ 构建缓存
2026-05-03 10:23:20 +08:00
commit 2536c937e3
400 changed files with 49040 additions and 0 deletions
@@ -0,0 +1,113 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 750 280" width="750" height="280" font-family="Arial, sans-serif">
+  <defs>
+    <marker id="dfe-arrow" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
+      <path d="M0,0 L8,3 L0,6" fill="#666"/>
+    </marker>
+  </defs>
+
+  <!-- Title -->
+  <text x="375" y="24" font-size="14" font-weight="bold" fill="#333" text-anchor="middle">Dual Encoder vs Fusion Encoder</text>
+
+  <!-- Divider -->
+  <line x1="375" y1="38" x2="375" y2="260" stroke="#ccc" stroke-width="1" stroke-dasharray="6,4"/>
+
+  <!-- === Left Panel: Dual Encoder === -->
+  <text x="185" y="52" font-size="12" font-weight="bold" fill="#3498db" text-anchor="middle">Dual Encoder</text>
+
+  <!-- Image input -->
+  <rect x="30" y="72" width="55" height="35" rx="4" fill="#eee" stroke="#ccc" stroke-width="1"/>
+  <rect x="37" y="78" width="15" height="12" rx="1" fill="#3498db" fill-opacity="0.3"/>
+  <rect x="55" y="82" width="12" height="10" rx="1" fill="#27ae60" fill-opacity="0.3"/>
+  <text x="57" y="118" font-size="8" fill="#999" text-anchor="middle">Image</text>
+
+  <!-- Text input -->
+  <rect x="30" y="155" width="55" height="35" rx="4" fill="#eee" stroke="#ccc" stroke-width="1"/>
+  <text x="57" y="175" font-size="8" fill="#666" text-anchor="middle">Text</text>
+  <text x="57" y="200" font-size="8" fill="#999" text-anchor="middle">Query</text>
+
+  <!-- Arrow to image encoder -->
+  <line x1="85" y1="90" x2="110" y2="90" stroke="#3498db" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+
+  <!-- Image Encoder -->
+  <rect x="115" y="68" width="100" height="44" rx="8" fill="#3498db" fill-opacity="0.12" stroke="#3498db" stroke-width="1.5"/>
+  <text x="165" y="87" font-size="10" fill="#333" text-anchor="middle">Image Encoder</text>
+  <text x="165" y="101" font-size="9" fill="#666" text-anchor="middle">(ViT)</text>
+
+  <!-- Arrow to text encoder -->
+  <line x1="85" y1="172" x2="110" y2="172" stroke="#e74c3c" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+
+  <!-- Text Encoder -->
+  <rect x="115" y="150" width="100" height="44" rx="8" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
+  <text x="165" y="169" font-size="10" fill="#333" text-anchor="middle">Text Encoder</text>
+  <text x="165" y="183" font-size="9" fill="#666" text-anchor="middle">(Transformer)</text>
+
+  <!-- Vectors -->
+  <line x1="215" y1="90" x2="248" y2="90" stroke="#3498db" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+  <line x1="215" y1="172" x2="248" y2="172" stroke="#e74c3c" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+
+  <!-- Vector boxes -->
+  <rect x="252" y="78" width="40" height="24" rx="4" fill="#3498db" fill-opacity="0.2" stroke="none"/>
+  <text x="272" y="94" font-size="9" fill="#3498db" text-anchor="middle">v_i</text>
+
+  <rect x="252" y="160" width="40" height="24" rx="4" fill="#e74c3c" fill-opacity="0.2" stroke="none"/>
+  <text x="272" y="176" font-size="9" fill="#e74c3c" text-anchor="middle">v_t</text>
+
+  <!-- Cosine similarity -->
+  <line x1="272" y1="102" x2="272" y2="158" stroke="#f39c12" stroke-width="1.5" stroke-dasharray="4,3"/>
+  <rect x="245" y="120" width="55" height="22" rx="4" fill="#f39c12" fill-opacity="0.12" stroke="#f39c12" stroke-width="1"/>
+  <text x="272" y="135" font-size="9" fill="#f39c12" text-anchor="middle" font-weight="bold">cos(v_i, v_t)</text>
+
+  <!-- Label -->
+  <text x="185" y="230" font-size="10" fill="#666" text-anchor="middle">Independent encoders</text>
+  <text x="185" y="245" font-size="10" fill="#27ae60" text-anchor="middle" font-weight="bold">Fast retrieval</text>
+  <text x="185" y="260" font-size="9" fill="#999" text-anchor="middle">O(1) similarity computation</text>
+
+  <!-- === Right Panel: Fusion Encoder === -->
+  <text x="565" y="52" font-size="12" font-weight="bold" fill="#9b59b6" text-anchor="middle">Fusion Encoder</text>
+
+  <!-- Image input -->
+  <rect x="400" y="72" width="55" height="35" rx="4" fill="#eee" stroke="#ccc" stroke-width="1"/>
+  <rect x="407" y="78" width="15" height="12" rx="1" fill="#3498db" fill-opacity="0.3"/>
+  <rect x="425" y="82" width="12" height="10" rx="1" fill="#27ae60" fill-opacity="0.3"/>
+  <text x="427" y="118" font-size="8" fill="#999" text-anchor="middle">Image</text>
+
+  <!-- Text input -->
+  <rect x="400" y="155" width="55" height="35" rx="4" fill="#eee" stroke="#ccc" stroke-width="1"/>
+  <text x="427" y="175" font-size="8" fill="#666" text-anchor="middle">Text</text>
+  <text x="427" y="200" font-size="8" fill="#999" text-anchor="middle">Query</text>
+
+  <!-- Image features -->
+  <line x1="455" y1="90" x2="490" y2="90" stroke="#3498db" stroke-width="1.2"/>
+  <!-- Text features -->
+  <line x1="455" y1="172" x2="490" y2="172" stroke="#e74c3c" stroke-width="1.2"/>
+
+  <!-- Token row (image tokens) -->
+  <rect x="492" y="80" width="12" height="12" rx="2" fill="#3498db" fill-opacity="0.4" stroke="none"/>
+  <rect x="506" y="80" width="12" height="12" rx="2" fill="#3498db" fill-opacity="0.4" stroke="none"/>
+  <rect x="520" y="80" width="12" height="12" rx="2" fill="#3498db" fill-opacity="0.4" stroke="none"/>
+  <rect x="534" y="80" width="12" height="12" rx="2" fill="#3498db" fill-opacity="0.4" stroke="none"/>
+
+  <!-- Token row (text tokens) -->
+  <rect x="492" y="165" width="12" height="12" rx="2" fill="#e74c3c" fill-opacity="0.4" stroke="none"/>
+  <rect x="506" y="165" width="12" height="12" rx="2" fill="#e74c3c" fill-opacity="0.4" stroke="none"/>
+  <rect x="520" y="165" width="12" height="12" rx="2" fill="#e74c3c" fill-opacity="0.4" stroke="none"/>
+
+  <!-- Arrows converging -->
+  <line x1="540" y1="90" x2="580" y2="115" stroke="#3498db" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+  <line x1="540" y1="172" x2="580" y2="148" stroke="#e74c3c" stroke-width="1.2" marker-end="url(#dfe-arrow)"/>
+
+  <!-- Cross-Attention Transformer -->
+  <rect x="585" y="100" width="130" height="62" rx="8" fill="#9b59b6" fill-opacity="0.12" stroke="#9b59b6" stroke-width="1.5"/>
+  <text x="650" y="122" font-size="10" fill="#333" text-anchor="middle">Cross-Attention</text>
+  <text x="650" y="136" font-size="10" fill="#333" text-anchor="middle">Transformer</text>
+  <text x="650" y="152" font-size="9" fill="#9b59b6" text-anchor="middle">(Deep Fusion)</text>
+
+  <!-- Bidirectional attention arrows inside -->
+  <line x1="605" y1="108" x2="695" y2="108" stroke="#9b59b6" stroke-width="0.8" stroke-dasharray="2,2"/>
+  <line x1="695" y1="155" x2="605" y2="155" stroke="#9b59b6" stroke-width="0.8" stroke-dasharray="2,2"/>
+
+  <!-- Label -->
+  <text x="565" y="230" font-size="10" fill="#666" text-anchor="middle">Token-level interaction</text>
+  <text x="565" y="245" font-size="10" fill="#27ae60" text-anchor="middle" font-weight="bold">Richer understanding</text>
+  <text x="565" y="260" font-size="9" fill="#999" text-anchor="middle">O(n*m) cross-attention cost</text>
+</svg>