fix: 修正附录目录嵌套，移除旧 officefile 附录文件
- 将 officefile/appendix/appendix/ 下的文件提升一级 - 旧 officefile 的 glossary/references/tools.md 移入 Archive Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -1,211 +0,0 @@
|
||||
# 附录C：关键术语表
|
||||
|
||||
本附录按章节整理书中涉及的关键中英文术语。
|
||||
|
||||
---
|
||||
|
||||
## A
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 自编码器 | Autoencoder, AE | 11 |
|
||||
| 注意力机制 | Attention | 8 |
|
||||
| 人类反馈强化学习 | RLHF | 10 |
|
||||
| 人工智能 | AI, Artificial Intelligence | 1 |
|
||||
| AI for Science | AI4S | 1 |
|
||||
| AI in Education | AIED | 1 |
|
||||
|
||||
## B
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 边界框 | Bounding Box | 6 |
|
||||
| 生物多样性 | Biodiversity | 24 |
|
||||
|
||||
## C
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 卷积神经网络 | CNN | 5, 6, 7 |
|
||||
| 卷积核 | Kernel/Filter | 5 |
|
||||
| 因果推断 | Causal Inference | - |
|
||||
| 连通性 | Connectivity | 25 |
|
||||
| 交叉熵 | Cross Entropy | 4 |
|
||||
|
||||
## D
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 扩散模型 | Diffusion Model | 11 |
|
||||
| 数字孪生 | Digital Twin | 14 |
|
||||
| 深度学习 | Deep Learning | 2 |
|
||||
| 设计生成式AI | Generative Design | 20 |
|
||||
|
||||
## E
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 生态系统服务 | Ecosystem Services | 24 |
|
||||
| 具身智能 | Embodied AI | 14 |
|
||||
| 编码器 | Encoder | 9 |
|
||||
| 解码器 | Decoder | 9 |
|
||||
|
||||
## F
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 特征图 | Feature Map | 5 |
|
||||
| 前馈网络 | FFN, Feed-Forward Network | 2, 9 |
|
||||
| 俯瞰 | Foundation Model | - |
|
||||
|
||||
## G
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 生成对抗网络 | GAN | 11 |
|
||||
| 生成式AI | AIGC | 1, 11, 16 |
|
||||
| 梯度下降 | Gradient Descent | 4 |
|
||||
| 图神经网络 | GNN | 2 |
|
||||
|
||||
## H
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| HITL | Human-in-the-Loop | 15 |
|
||||
| 隐藏层 | Hidden Layer | 3 |
|
||||
| 超参数 | Hyperparameter | - |
|
||||
|
||||
## I
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 交并比 | IoU | 6 |
|
||||
| 图像分类 | Image Classification | 6 |
|
||||
| 实例分割 | Instance Segmentation | 7 |
|
||||
|
||||
## K
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 键 | Key | 8 |
|
||||
| 核函数 | Kernel Function | - |
|
||||
|
||||
## L
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 大语言模型 | LLM | 10 |
|
||||
| 损失函数 | Loss Function | 4 |
|
||||
| 学习率 | Learning Rate | 4 |
|
||||
| LoRA | Low-Rank Adaptation | 12 |
|
||||
| 潜在空间 | Latent Space | 11 |
|
||||
|
||||
## M
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 多头注意力 | Multi-Head Attention | 8 |
|
||||
| 多层感知机 | MLP | 3, 4 |
|
||||
| 多模态 | Multimodal | 10 |
|
||||
| MCP | Model Context Protocol | 15 |
|
||||
| 平均精度 | mAP | 6 |
|
||||
|
||||
## N
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 归一化 | Normalization | 9 |
|
||||
| 神经网络 | Neural Network | 2 |
|
||||
| 非极大值抑制 | NMS | 6 |
|
||||
|
||||
## O
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 目标检测 | Object Detection | 6 |
|
||||
| 优化器 | Optimizer | 4 |
|
||||
| One-Stage检测器 | One-Stage Detector | 6 |
|
||||
|
||||
## P
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 位置编码 | Positional Encoding | 8 |
|
||||
| 池化 | Pooling | 5 |
|
||||
| 提示工程 | Prompt Engineering | 10 |
|
||||
| 预训练 | Pre-training | 10 |
|
||||
| 像素 | Pixel | 7 |
|
||||
|
||||
## Q
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 查询 | Query | 8 |
|
||||
| Q学习 | Q-Learning | 14 |
|
||||
|
||||
## R
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| RAG | Retrieval-Augmented Generation | 10 |
|
||||
| ReAct | Reasoning + Acting | 13 |
|
||||
| 强化学习 | RL, Reinforcement Learning | 14 |
|
||||
| 循环神经网络 | RNN | 2 |
|
||||
| 残差连接 | Residual Connection | 9 |
|
||||
| 值 | Value | 8 |
|
||||
| 感受野 | Receptive Field | 5 |
|
||||
|
||||
## S
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| Self-Attention | 自注意力 | 8 |
|
||||
| 语义分割 | Semantic Segmentation | 7 |
|
||||
| Scaling Law | 缩放定律 | 2 |
|
||||
| Sigmoid | 激活函数 | 4 |
|
||||
| Softmax | 激活函数 | 4 |
|
||||
| 境况 | State | 14 |
|
||||
| 潜变量 | Latent Variable | 11 |
|
||||
| 支持向量机 | SVM | - |
|
||||
|
||||
## T
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| Transformer | Transformer架构 | 9 |
|
||||
| 拓扑优化 | Topology Optimization | 21 |
|
||||
| Token | 令牌/词元 | 9 |
|
||||
| 目标检测 | Two-Stage Detector | 6 |
|
||||
|
||||
## U
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 万能逼近定理 | Universal Approximation Theorem | 2 |
|
||||
| U-Net | 分割网络架构 | 7 |
|
||||
|
||||
## V
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| VAE | Variational Autoencoder | 11 |
|
||||
| 向量数据库 | Vector Database | 10 |
|
||||
| 视觉Transformer | Vision Transformer | 5 |
|
||||
|
||||
## W
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| 权重 | Weight | 3 |
|
||||
| 权重共享 | Weight Sharing | 5 |
|
||||
| 权重衰减 | Weight Decay | - |
|
||||
|
||||
## Y
|
||||
|
||||
| 中文 | 英文 | 章节 |
|
||||
|-----|------|------|
|
||||
| YOLO | You Only Look Once | 6 |
|
||||
|
||||
---
|
||||
|
||||
**更新日期**：2026年4月
|
||||
@@ -1,111 +0,0 @@
|
||||
# 参考文献
|
||||
|
||||
本部分整理教材中引用的论文、书籍和在线资源。
|
||||
|
||||
---
|
||||
|
||||
## 论文
|
||||
|
||||
### 基础理论
|
||||
|
||||
- Universal Approximation Theorem (1989)
|
||||
- Scaling Laws for Neural Language Models (2020)
|
||||
|
||||
### 计算机视觉
|
||||
|
||||
- AlexNet (2012) - ImageNet Classification with Deep Convolutional Neural Networks
|
||||
- ResNet (2015) - Deep Residual Learning for Image Recognition
|
||||
- YOLO (2016) - You Only Look Once: Unified, Real-Time Object Detection
|
||||
- U-Net (2015) - Convolutional Networks for Biomedical Image Segmentation
|
||||
|
||||
### Transformer与大模型
|
||||
|
||||
- Attention Is All You Need (2017)
|
||||
- BERT: Pre-training of Deep Bidirectional Transformers (2018)
|
||||
- GPT-3: Language Models are Few-Shot Learners (2020)
|
||||
- Training Language Models to Follow Instructions with Human Feedback (2022)
|
||||
|
||||
### 生成式AI
|
||||
|
||||
- Denoising Diffusion Probabilistic Models (2020)
|
||||
- High-Resolution Image Synthesis with Latent Diffusion Models (2022)
|
||||
- ControlNet (2023)
|
||||
|
||||
### AI Agent
|
||||
|
||||
- LLM Powered Autonomous Agents (2023)
|
||||
- ReAct: Synergizing Reasoning and Acting in Language Models (2022)
|
||||
|
||||
---
|
||||
|
||||
## 书籍
|
||||
|
||||
### 深度学习
|
||||
|
||||
- Deep Learning (Ian Goodfellow et al.)
|
||||
- Neural Networks and Deep Learning (Michael Nielsen)
|
||||
|
||||
### 强化学习
|
||||
|
||||
- Reinforcement Learning: An Introduction (Sutton & Barto)
|
||||
|
||||
---
|
||||
|
||||
## 在线资源
|
||||
|
||||
### 课程
|
||||
|
||||
- CS231n: Convolutional Neural Networks for Visual Recognition
|
||||
- Fast.ai Practical Deep Learning for Coders
|
||||
|
||||
### 工具文档
|
||||
|
||||
- PyTorch: https://pytorch.org/docs/
|
||||
- Ultralytics YOLO: https://docs.ultralytics.com/
|
||||
- LangChain: https://python.langchain.com/
|
||||
|
||||
### 博客
|
||||
|
||||
- Lil'Log (Lilian Weng): https://lilianweng.github.io/
|
||||
- The Illustrated Transformer: https://jalammar.github.io/illustrated-transformer/
|
||||
|
||||
---
|
||||
|
||||
## 设计AI相关
|
||||
|
||||
### 学术期刊
|
||||
|
||||
- Landscape and Urban Planning
|
||||
- Environment and Planning B: Urban Analytics and City Science
|
||||
- Automation in Construction
|
||||
|
||||
### 会议
|
||||
|
||||
- CAAD Futures
|
||||
- ACADIA
|
||||
- eCAADe
|
||||
|
||||
---
|
||||
|
||||
## 数据集
|
||||
|
||||
### 计算机视觉
|
||||
|
||||
- ImageNet
|
||||
- COCO (Common Objects in Context)
|
||||
- MNIST
|
||||
|
||||
### 空间数据
|
||||
|
||||
- OpenStreetMap
|
||||
- 路网数据、POI数据等
|
||||
|
||||
---
|
||||
|
||||
## 许可说明
|
||||
|
||||
部分内容引用自公开资源，遵循相应许可协议使用。
|
||||
|
||||
---
|
||||
|
||||
**最后更新**：2026年4月
|
||||
@@ -1,251 +0,0 @@
|
||||
# 附录A：编程工具与资源
|
||||
|
||||
本附录整理AI学习和实践所需的编程工具、框架和资源。
|
||||
|
||||
---
|
||||
|
||||
## Python环境配置
|
||||
|
||||
### Anaconda/Miniconda
|
||||
|
||||
| 工具 | 大小 | 特点 | 下载地址 |
|
||||
|-----|------|------|---------|
|
||||
| Anaconda | ~500MB | 预装常用库 | [anaconda.com](https://www.anaconda.com/download) |
|
||||
| Miniconda | ~50MB | 精简安装 | [docs.conda.io](https://docs.conda.io/en/latest/miniconda.html) |
|
||||
|
||||
### 安装步骤
|
||||
|
||||
```bash
|
||||
# 1. 下载并安装Miniconda
|
||||
# 2. 创建虚拟环境
|
||||
conda create -n ai-env python=3.10
|
||||
|
||||
# 3. 激活环境
|
||||
conda activate ai-env
|
||||
|
||||
# 4. 安装核心库
|
||||
pip install torch torchvision numpy pandas scipy
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 深度学习框架
|
||||
|
||||
### PyTorch
|
||||
|
||||
```bash
|
||||
pip install torch torchvision torchaudio
|
||||
```
|
||||
|
||||
**特点**：
|
||||
- 动态计算图
|
||||
- 研究友好
|
||||
- 广泛的社区支持
|
||||
|
||||
**资源**：
|
||||
- [官方文档](https://pytorch.org/docs/)
|
||||
- [中文教程](https://pytorch.zhangxiann.com/)
|
||||
|
||||
### TensorFlow
|
||||
|
||||
```bash
|
||||
pip install tensorflow
|
||||
```
|
||||
|
||||
**特点**：
|
||||
- 生产部署优化
|
||||
- Keras高级API
|
||||
- 跨平台支持
|
||||
|
||||
---
|
||||
|
||||
## 计算机视觉工具
|
||||
|
||||
### OpenCV
|
||||
|
||||
```bash
|
||||
pip install opencv-python
|
||||
```
|
||||
|
||||
**功能**：图像处理、视频分析
|
||||
|
||||
### Ultralytics YOLO
|
||||
|
||||
```bash
|
||||
pip install ultralytics
|
||||
```
|
||||
|
||||
**功能**：目标检测、实例分割
|
||||
|
||||
**使用示例**：
|
||||
```python
|
||||
from ultralytics import YOLO
|
||||
|
||||
model = YOLO('yolov8n.pt')
|
||||
results = model('image.jpg')
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## AIGC工具链
|
||||
|
||||
### Stable Diffusion
|
||||
|
||||
**WebUI**：[Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
|
||||
|
||||
**ComfyUI**：[GitHub](https://github.com/comfyanonymous/ComfyUI)
|
||||
|
||||
**API调用**：
|
||||
```python
|
||||
from diffusers import StableDiffusionPipeline
|
||||
|
||||
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
|
||||
image = pipe("a photo of an astronaut riding a horse on mars").images[0]
|
||||
```
|
||||
|
||||
### ControlNet
|
||||
|
||||
```python
|
||||
from diffusers import StableDiffusionControlNetPipeline
|
||||
|
||||
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny")
|
||||
pipe = StableDiffusionControlNetPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", controlnet=controlnet)
|
||||
```
|
||||
|
||||
### Midjourney
|
||||
|
||||
**平台**：Discord
|
||||
**文档**：[docs.midjourney.com](https://docs.midjourney.com/)
|
||||
|
||||
---
|
||||
|
||||
## Agent开发框架
|
||||
|
||||
### LangChain
|
||||
|
||||
```bash
|
||||
pip install langchain langchain-openai
|
||||
```
|
||||
|
||||
**功能**：LLM应用开发框架
|
||||
|
||||
**核心组件**：
|
||||
- Models：LLM接口
|
||||
- Prompts：提示管理
|
||||
- Chains：链式调用
|
||||
- Agents：智能体
|
||||
- Memory：记忆管理
|
||||
|
||||
### LangGraph
|
||||
|
||||
```bash
|
||||
pip install langgraph
|
||||
```
|
||||
|
||||
**功能**：状态机式Agent开发
|
||||
|
||||
### LlamaIndex
|
||||
|
||||
```bash
|
||||
pip install llama-index
|
||||
```
|
||||
|
||||
**功能**：数据索引与检索（RAG）
|
||||
|
||||
---
|
||||
|
||||
## 开发工具
|
||||
|
||||
### VSCode
|
||||
|
||||
**AI开发常用插件**：
|
||||
- Python
|
||||
- Pylance
|
||||
- Jupyter
|
||||
- Copilot
|
||||
|
||||
### Cursor
|
||||
|
||||
**特点**：AI原生IDE
|
||||
**网址**：[cursor.com](https://cursor.com/)
|
||||
|
||||
### Jupyter Lab
|
||||
|
||||
```bash
|
||||
pip install jupyterlab
|
||||
jupyter lab
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 在线学习资源
|
||||
|
||||
### 课程
|
||||
|
||||
| 名称 | 平台 | 链接 |
|
||||
|-----|------|------|
|
||||
| CS231n | Stanford | [cs231n.stanford.edu](http://cs231n.stanford.edu/) |
|
||||
| Fast.ai | fast.ai | [course.fast.ai](https://course.fast.ai/) |
|
||||
| 吴恩达深度学习 | Coursera | [coursera.org/specializations/deep-learning](https://www.coursera.org/specializations/deep-learning) |
|
||||
|
||||
### 博客与文档
|
||||
|
||||
- [Lil'Log](https://lilianweng.github.io/) - AI深度文章
|
||||
- [The Illustrated Transformer](https://jalammar.github.io/illustrated-transformer/)
|
||||
- [Distill.pub](https://distill.pub/) - 可视化论文
|
||||
|
||||
### 数据集
|
||||
|
||||
| 数据集 | 内容 | 链接 |
|
||||
|-------|------|------|
|
||||
| ImageNet | 图像分类 | [image-net.org](https://www.image-net.org/) |
|
||||
| COCO | 目标检测 | [cocodataset.org](https://cocodataset.org/) |
|
||||
| OpenStreetMap | 地图数据 | [openstreetmap.org](https://www.openstreetmap.org/) |
|
||||
|
||||
---
|
||||
|
||||
## 模型资源
|
||||
|
||||
### Hugging Face
|
||||
|
||||
**网址**：[huggingface.co](https://huggingface.co/)
|
||||
|
||||
**功能**：
|
||||
- 模型仓库
|
||||
- 数据集
|
||||
- Spaces在线演示
|
||||
|
||||
### 常用模型
|
||||
|
||||
| 任务 | 推荐模型 | Hugging Face ID |
|
||||
|-----|---------|----------------|
|
||||
| 文生图 | Stable Diffusion XL | stabilityai/stable-diffusion-xl-base-1.0 |
|
||||
| 目标检测 | YOLOv8 | Ultralytics |
|
||||
| 语义分割 | SAM | segment-anything |
|
||||
| 大语言模型 | Llama 3 | meta-llama/Meta-Llama-3-8B |
|
||||
|
||||
---
|
||||
|
||||
## 硬件资源
|
||||
|
||||
### 云平台
|
||||
|
||||
| 平台 | 特点 | 适合场景 |
|
||||
|-----|------|---------|
|
||||
| Google Colab | 免费GPU | 学习实验 |
|
||||
| Kaggle Notebooks | 免费GPU | 竞赛 |
|
||||
| AutoDL | 按时计费 | 中期项目 |
|
||||
| 阿里云PAI | 国内稳定 | 生产部署 |
|
||||
|
||||
### 本地GPU
|
||||
|
||||
推荐配置：
|
||||
- GPU：RTX 3060 (12GB) 或更高
|
||||
- 内存：16GB+
|
||||
- 存储：至少100GB SSD
|
||||
|
||||
---
|
||||
|
||||
## 最后更新
|
||||
|
||||
2026年4月
|
||||
Reference in New Issue
Block a user